Awesome-Human-Agent-Collaboration-Interaction-Systems

KO | EN

gitlite — search

#python #ai #typescript #llm #go #linux #docker #macos #java #awesome-list #security #mcp #openai #open-source

Awesome-Human-Agent-Collaboration-Interaction-Systems

(★ 232)

[ACL 2026] LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey | Awesome Human-Agent Collaboration | Human-AI Collaboration

파일 탐색기

최종 버전 다운로드 (.zip)

- human_feedback.png
- human_feedback_0.png
- overview_llm_has.jpg
- taxonomy.png
.gitignore
README.md

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Awesome LLM-Based Human-Agent Collaboration and Interaction Systems

> 🎉 **Our survey has been accepted to ACL 2026!**

[![ACL 2026](https://img.shields.io/badge/ACL%202026-Accepted-brightgreen.svg)](https://arxiv.org/abs/2505.00753)
![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)
[![arXiv](https://img.shields.io/badge/arXiv-Human_Agent_Collaboration-b31b1b.svg)](https://arxiv.org/abs/2505.00753)
[![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg)]()
[![Contribution Welcome](https://img.shields.io/badge/Contributions-welcome-blue)]()
![Last Commit](https://img.shields.io/github/last-commit/HenryPengZou/Awesome-Human-Agent-Collaboration-Interaction-Systems)
[![GitHub stars](https://img.shields.io/github/stars/HenryPengZou/Awesome-Human-Agent-Collaboration-Interaction-Systems)](https://github.com/HenryPengZou/Awesome-Human-Agent-Collaboration-Interaction-Systems)

![image](https://raw.githubusercontent.com/HenryPengZou/Awesome-Human-Agent-Collaboration-Interaction-Systems/main/images/overview_llm_has.jpg)

Welcome to Awesome-Human-Agent-Collaboration-Interaction-Systems! 🚀 This is the repo for our [Survey on LLM-Based Human-Agent Collaboration and Interaction Systems](https://arxiv.org/abs/2505.00753), **accepted to ACL 2026**.

## 🌟 Introduction

Recent advances in large language models (LLMs) have sparked growing interest in building fully autonomous agents. However, **fully autonomous LLM-based agents** still face significant challenges, including ***(1) limited reliability due to hallucinations***, ***(2) difficulty in handling complex tasks***, and ***(3) substantial safety and ethical risks***, all of which limit their feasibility and trustworthiness in real-world applications.

**LLM-based human-agent collaboration systems are interactive frameworks where humans actively provide** ***(1) additional information***, ***(2) feedback***, or ***(3) control*** during interaction with LLM-powered agents to *enhance system performance, reliability, and safety*. These human-agent collaboration systems enable humans and LLM-based agents to collaborate effectively by leveraging their complementary strengths. For a detailed introduction, please refer to our survey paper: [LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey](https://arxiv.org/abs/2505.00753).

Our goal with this project is to build an exhaustive collection of awesome resources relevant to LLM-Based Human-Agent/AI Collaboration and Interaction Systems, encompassing papers, repositories, and more to foster further research and innovation in this rapidly evolving interdisciplinary field of human-ai collaboration. 🤗 ***Contributions are welcome!*** 🤗 *If you have recommended papers, resources or suggestions, please submit pull requests, open issues or contact us. We will keep updating our repo & survey paper.*

## 📄 Contents

- [📄 Latest Research Papers](#-latest-research-papers)
- [📚 Applications, Datasets & Benchmarks](#-applications-datasets--benchmarks)
    - [💻 Web Navigation & Computer Use](#-web-navigation--computer-use)
    - [👨🏻‍💻 Software Engineering, Coding](#-software-engineering-coding)
    - [🤖 Embodied AI, Robotics](#-embodied-ai-robotics)
    - [💬 Conversation System](#-conversation-system)
    - [📊 Data Science, Scientific Discovery](#-data-science-scientific-discovery)
    - [🎮 Gaming](#-gaming)
    - [💰 Finance](#-finance)
    - [🏥 Healthcare, Medicine](#-healthcare-medicine)
    - [🧩 General-Purpose Assistants, Cross-Domain](#-general-purpose-assistants-cross-domain)
    - [🛍️ Retail, Telecom](#-retail-telecom)
    - [🛩️ Travel](#-travel)
    - [✍️ Writing](#-writing)
- [🔍 Taxonomy](#-taxonomy)
    - [🤝 Human Feedback](#-human-feedback)
    - [🔄 Interaction](#-interaction)
    - [🎛️ Orchestration](#-orchestration)
    - [💬 Communication](#-communication)
- [📌 Contributing](#-contributing)
- [📝 Citation](#-citation)

## 📄 Latest Research Papers
 ([©️click here back to table of contents👆🏻](#contents))

🤗 *Contributions are welcome! If you have recommended papers and resources, please submit pull requests or open issues.*

- **[2026-07-18]** [arXiv 2026] [Just A Rather Very Intelligent Spoken Agent (JarvisBench)](https://arxiv.org/abs/2607.16610) [[Project]](https://cchen1436.github.io/jarvis)

- **[2026-07-07]** [arXiv 2026] [LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability](https://arxiv.org/abs/2607.06157) [![GitHub stars](https://img.shields.io/github/stars/wcx21/deliberative-collaboration-agents?style=social)](https://github.com/wcx21/deliberative-collaboration-agents)

- **[2026-07-05]** [arXiv 2026] [HAS-Bench: Evaluating LLM-Based Human-Agent Systems under Configurable Human Participation](https://arxiv.org/abs/2607.04329)

- **[2026-06-17]** [arXiv 2026] [Uncertainty Decomposition for Clarification Seeking in LLM Agents](https://arxiv.org/abs/2606.19559)

- **[2026-06-17]** [arXiv 2026] [Learning User Simulators with Turing Rewards](https://arxiv.org/abs/2606.19336)

- **[2026-06-11]** [arXiv 2026] [Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents (TRACE)](https://arxiv.org/abs/2606.13174) [![GitHub stars](https://img.shields.io/github/stars/YujunZhou/tellonce?style=social)](https://github.com/YujunZhou/tellonce)

- **[2026-06-07]** [arXiv 2026] [PerspectiveGap: A Benchmark for Multi-Agent Orchestration Prompting](https://arxiv.org/abs/2606.08878) [![GitHub stars](https://img.shields.io/github/stars/WhymustIhaveaname/PerspectiveGap?style=social)](https://github.com/WhymustIhaveaname/PerspectiveGap)

- **[2026-06-04]** [arXiv 2026] [Re-Centering Humans in LLM Personalization](https://arxiv.org/abs/2606.06614)

- **[2026-06-04]** [ICML 2026] [CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement](https://arxiv.org/abs/2606.05793)

- **[2026-06-03]** [arXiv 2026] [Human Oversight of Agentic Systems in Practice: Examining the Oversight Work, Challenges, and Heuristics of Developers Using Software Agents](https://arxiv.org/abs/2606.05391)

- **[2026-06-02]** [arXiv 2026] [Uncertainty-Aware Clarification in LLM Agents with Information Gain](https://arxiv.org/abs/2606.03135)

- **[2026-05-27]** [FAccT 2026] [Not All Uncertainty Is Equal: How Uncertainty Granularity Shapes Human Verification in LLM-Assisted Decision Making](https://arxiv.org/abs/2605.28571)

- **[2026-05-26]** [arXiv 2026] [VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions](https://arxiv.org/abs/2605.27141) [![GitHub stars](https://img.shields.io/github/stars/meituan-longcat/VitaBench-2.0?style=social)](https://github.com/meituan-longcat/VitaBench-2.0)

- **[2026-05-23]** [arXiv 2026] [Reframing LLM Agent Security as an Agent-Human Interaction Problem](https://arxiv.org/abs/2605.24309)

- **[2026-05-19]** [arXiv 2026] [Reinforcing Human Behavior Simulation via Verbal Feedback (DITTO & SOUL)](https://arxiv.org/abs/2605.20506)

- **[2026-05-11]** [arXiv 2026] [ECHO: Explainable Co-editing with Human-in-the-loop Operations for Presentation Refinement](https://arxiv.org/abs/2606.09851)

- **[2026-05-09]** [arXiv 2026] [AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators](https://arxiv.org/abs/2605.08647)

- **[2026-05-08]** [arXiv 2026] [SalesSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators](https://arxiv.org/abs/2605.08334)

- **[2026-04-24]** [arXiv 2026] [A Decoupled Human-in-the-Loop System for Controlled Autonomy in Agentic Workflows](https://arxiv.org/abs/2604.23049)

- **[2026-04-20]** [arXiv 2026] [CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks](https://arxiv.org/abs/2606.09833)

- **[2026-04-07]** [arXiv 2026] [Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge](https://arxiv.org/abs/2604.05593)

- **[2026-04-01]** [arXiv 2026] [When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation](https://arxiv.org/abs/2604.00892) [![GitHub stars](https://img.shields.io/github/stars/HenryPengZou/InterruptBench?style=social)](https://github.com/HenryPengZou/InterruptBench)

- **[2026-03-30]** [arXiv 2026] [ViviDoc: Generating Interactive Documents through Human-Agent Collaboration](https://arxiv.org/pdf/2603.01912) [![GitHub stars](https://img.shields.io/github/stars/MisterBrookT/vividoc?style=social)](https://github.com/MisterBrookT/vividoc)

- **[2026-03-27]** [arXiv 2026] [Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents](https://arxiv.org/abs/2603.26233)

- **[2026-03-21]** [arXiv 2026] [User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction (VARS)](https://arxiv.org/abs/2603.20939) [![GitHub stars](https://img.shields.io/github/stars/YurenHao0426/VARS?style=social)](https://github.com/YurenHao0426/VARS)

- **[2026-03-20]** [arXiv 2026] [LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks](https://arxiv.org/abs/2604.13072) [![GitHub stars](https://img.shields.io/github/stars/Mosi-AI/LiveClawBench?style=social)](https://github.com/Mosi-AI/LiveClawBench)

- **[2026-03-19]** [arXiv 2026] [AgentDS: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science](https://arxiv.org/abs/2603.19005) [[Project]](https://agentds.org/)

- **[2026-02-28]** [arXiv 2026] [InfoPO: Information-Driven Policy Optimization for User-Centric Agents](https://arxiv.org/abs/2603.00656) [![GitHub stars](https://img.shields.io/github/stars/kfq20/InfoPO?style=social)](https://github.com/kfq20/InfoPO)

- **[2026-02-19]** [arXiv 2026] [Modeling Distinct Human Interaction in Web Agents (CowCorpus)](https://arxiv.org/abs/2602.17588)

- **[2026-02-18]** [arXiv 2026] [Learning Personalized Agents from Human Feedback](https://arxiv.org/abs/2602.16173) [![GitHub stars](https://img.shields.io/github/stars/facebookresearch/PAHF?style=social)](https://github.com/facebookresearch/PAHF)

- **[2026-02-18]** [arXiv 2026] [Overseeing Agents Without Constant Oversight: Challenges and Opportunities](https://arxiv.org/abs/2602.16844)

- **[2026-01-10]** [arXiv 2026] [Value of Information: A Framework for Human-Agent Communication](https://arxiv.org/abs/2601.06407)

- **[2026-01-01]** [arXiv 2026] [Progressive Ideation using an Agentic AI Framework for Human-AI Co-Creation (MIDAS)](https://arxiv.org/abs/2601.00475)

- **[2025-11-30]** [arXiv 2025] [CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding](https://arxiv.org/abs/2512.04111)

- **[2025-11-04]** [arXiv 2025] [Training Proactive and Personalized LLM Agents](https://arxiv.org/abs/2511.02208) [![GitHub stars](https://img.shields.io/github/stars/sunnweiwei/PPP-Agent?style=social)](https://github.com/sunnweiwei/PPP-Agent)

- **[2025-10-15]** [arXiv 2025] [Training LLM Agents to Empower Humans](https://arxiv.org/abs/2510.13709) [![GitHub stars](https://img.shields.io/github/stars/festusev/codegen_empowerment?style=social)](https://github.com/festusev/codegen_empowerment)

- **[2025-10-10]** [arXiv 2025] [How can we assess human-agent interactions? Case studies in software agent design](https://arxiv.org/abs/2510.09801v2)

- **[2025-10-07]** [arXiv 2025] [RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback](https://arxiv.org/abs/2510.06186) [![GitHub stars](https://img.shields.io/github/stars/ChunyuMiao98/RECODE-H?style=social)](https://github.com/ChunyuMiao98/RECODE-H)

- **[2025-09-24]** [arXiv 2025] [UserRL: Training Proactive User-Centric Agent via Reinforcement Learning](https://arxiv.org/abs/2509.19736) [![GitHub stars](https://img.shields.io/github/stars/SalesforceAIResearch/UserRL?style=social)](https://github.com/SalesforceAIResearch/UserRL)
  
- **[2025-08-26]** [arXiv 2025] [MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use](https://arxiv.org/abs/2508.18669) [![GitHub stars](https://img.shields.io/github/stars/zzwkk/MUA-RL?style=social)](https://github.com/zzwkk/MUA-RL)

- **[2025-08-20]** [arXiv 2025] [aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists](https://arxiv.org/abs/2508.15126) [![GitHub stars](https://img.shields.io/github/stars/aixiv-org/aiXiv?style=social)](https://github.com/aixiv-org/aiXiv)
  
- **[2025-07-31]** [arXiv 2025] [MemoCue: Empowering LLM-Based Agents for Human Memory Recall via Strategy-Guided Querying](https://arxiv.org/abs/2507.23633)

- **[2025-07-30]** [arXiv 2025] [Magentic-UI: Towards Human-in-the-loop Agentic Systems](https://www.arxiv.org/abs/2507.22358) [![GitHub stars](https://img.shields.io/github/stars/microsoft/magentic-ui?style=social)](https://github.com/microsoft/magentic-ui)

- **[2025-07-29]** [arXiv 2025] [UserBench: An Interactive Gym Environment for User-Centric Agents](https://arxiv.org/abs/2507.22034) [![GitHub stars](https://img.shields.io/github/stars/SalesforceAIResearch/UserBench?style=social)](https://github.com/SalesforceAIResearch/UserBench)

- **[2025-07-28]** [arXiv 2025] [GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis](https://arxiv.org/abs/2507.21035) [![GitHub stars](https://img.shields.io/github/stars/Liu-Hy/GenoMAS?style=social)](https://github.com/Liu-Hy/GenoMAS)

- **[2025-07-23]** [arXiv 2025] [Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance](https://www.arxiv.org/abs/2507.17131) [![GitHub stars](https://img.shields.io/github/stars/yf-he/aria?style=social)](https://github.com/yf-he/aria)

- **[2025-07-21]** [arXiv 2025] [Interaction as Intelligence: Deep Research With Human-AI Partnership](https://arxiv.org/abs/2507.15759)

- **[2025-06-13]** [arXiv 2025] [Interaction, Process, Infrastructure: A Unified Architecture for Human-Agent Collaboration](https://arxiv.org/abs/2506.11718)

- **[2025-06-11]** [arXiv 2025] [A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy](https://arxiv.org/abs/2506.09420) [![GitHub stars](https://img.shields.io/github/stars/HenryPengZou/Awesome-Human-Agent-Collaboration-Interaction-Systems?style=social)](https://github.com/HenryPengZou/Awesome-Human-Agent-Collaboration-Interaction-Systems)

- **[2025-06-09]** [arXiv 2025] [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://arxiv.org/abs/2506.07982) [![GitHub stars](https://img.shields.io/github/stars/sierra-research/tau2-bench?style=social)](https://github.com/sierra-research/tau2-bench)

- **[2025-06-06]** [arXiv 2025] [Future of Work with AI Agents: Auditing Automation and Augmentation Potential across the U.S. Workforce](https://arxiv.org/abs/2506.06576) [![GitHub stars](https://img.shields.io/github/stars/SALT-NLP/workbank?style=social)](https://github.com/SALT-NLP/workbank)

- **[2025-05-24]** [ICLR 2025] [Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training](https://arxiv.org/abs/2406.00222) [[Code]](https://github.com/google-research/google-research/tree/master/learning_to_clarify)

- **[2025-05-23]** [arXiv 2025] [Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control](https://arxiv.org/abs/2505.18279v1)

- **[2025-05-21]** [arXiv 2025] [Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild](https://arxiv.org/abs/2505.16023) [![GitHub stars](https://img.shields.io/github/stars/microsoft/prototypical-hai-collaborations?style=social)](https://github.com/microsoft/prototypical-hai-collaborations)

- **[2025-05-16]** [arXiv 2025] [XtraGPT: LLMs for Human-AI Collaboration on Controllable Academic Paper Revision](https://arxiv.org/abs/2505.11336) [![GitHub stars](https://img.shields.io/github/stars/NuoJohnChen/XtraGPT?style=social)](https://github.com/NuoJohnChen/XtraGPT)

- **[2025-05-05]** [arXiv 2025] [SymbioticRAG: Enhancing Document Intelligence Through Human-LLM Symbiotic Collaboration](https://web3.arxiv.org/abs/2505.02418)

- **[2025-05-01]** [arXiv 2025] [LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey](https://arxiv.org/abs/2505.00753) [![GitHub stars](https://img.shields.io/github/stars/HenryPengZou/Awesome-Human-Agent-Collaboration-Interaction-Systems?style=social)](https://github.com/HenryPengZou/Awesome-Human-Agent-Collaboration-Interaction-Systems)

- **[2025-04-13]** [arXiv 2025] [EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety](https://arxiv.org/abs/2504.09689) [![GitHub stars](https://img.shields.io/github/stars/1akaman/EmoAgent?style=social)](https://github.com/1akaman/EmoAgent)

- **[2025-04-11]** [arXiv 2025] [MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft](https://arxiv.org/abs/2504.08388) [![GitHub stars](https://img.shields.io/github/stars/microsoft/MineWorld?style=social)](https://github.com/microsoft/MineWorld)

- **[2025-04-04]** [arXiv 2025] [APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay](https://arxiv.org/abs/2504.03601)

- **[2025-03-24]** [ACL 2025 Findings] [SPHERE: An Evaluation Card for Human-AI Systems](https://arxiv.org/abs/2504.07971) [![GitHub stars](https://img.shields.io/github/stars/sphere-eval/sphere-eval.github.io?style=social)](https://github.com/sphere-eval/sphere-eval.github.io)

- **[2025-03-19]** [arXiv 2025] [SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks](https://arxiv.org/abs/2503.15478) [![GitHub stars](https://img.shields.io/github/stars/facebookresearch/sweet_rl?style=social)](https://github.com/facebookresearch/sweet_rl)

- **[2025-03-10]** [arXiv 2025] [Experimental Exploration: Investigating Cooperative Interaction Behavior Between Humans and Large Language Model Agents](https://arxiv.org/abs/2503.07320)

- **[2025-03-04]** [arXiv 2025] [FinArena: A Human-Agent Collaboration Framework for Financial Market Analysis and Forecasting](https://arxiv.org/abs/2503.02692)
  
- **[2025-03-03]** [ICML 2025] [M3HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality](https://openreview.net/forum?id=2Sl6Ex7Vmo)

- **[2025-02-27]** [ICLR 2025] [ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments](https://arxiv.org/abs/2502.19852) [![GitHub stars](https://img.shields.io/github/stars/stovecat/convcodeworld?style=social)](https://github.com/stovecat/convcodeworld)

- **[2025-02-17]** [ACL 2025] [Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration](https://arxiv.org/abs/2502.11882) [![GitHub stars](https://img.shields.io/github/stars/sjtu-marl/DPT-Agent?style=social)](https://github.com/sjtu-marl/DPT-Agent)

- **[2025-02-02]** [ICML 2025] [CollabLLM: From Passive Responders to Active Collaborators](https://openreview.net/forum?id=DmH4HHVb3y) [![GitHub stars](https://img.shields.io/github/stars/Wuyxin/collabllm?style=social)](https://github.com/Wuyxin/collabllm)

- **[2025-01-28]** [NAACL 2025 Demo] [CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigation](https://arxiv.org/abs/2501.16609)

- **[2024-12-25]** [IROS 2024] [To Help or Not to Help: LLM-based Attentive Support for Human-Robot Group Interactions](https://ieeexplore.ieee.org/abstract/document/10801517) [![GitHub stars](https://img.shields.io/github/stars/HRI-EU/AttentiveSupport?style=social)](https://github.com/HRI-EU/AttentiveSupport)

- **[2024-12-20]** [arXiv 2024] [Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration](https://arxiv.org/abs/2412.15701) [![GitHub stars](https://img.shields.io/github/stars/SALT-NLP/collaborative-gym?style=social)](https://github.com/SALT-NLP/collaborative-gym)

- **[2024-12-08]** [arXiv 2024] [Towards Modeling Human-Agentic Collaborative Workflows: A BPMN Extension](https://arxiv.org/abs/2412.05958)
 [![GitHub stars](https://img.shields.io/github/stars/BESSER-PEARL/agentic-bpmn?style=social)](https://github.com/BESSER-PEARL/agentic-bpmn)

- **[2024-11-26]** [arXiv 2024] [Effect of Adaptive Communication Support on LLM-powered Human-Robot Collaboration](https://arxiv.org/abs/2412.06808)

- **[2024-10-31]** [ICLR 2025] [PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks](https://arxiv.org/abs/2411.00081) [![GitHub stars](https://img.shields.io/github/stars/facebookresearch/partnr-planner?style=social)](https://github.com/facebookresearch/partnr-planner)

- **[2024-10-30]** [ICLR 2025] [ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration](https://openreview.net/forum?id=nfKfAzkiez) [![GitHub stars](https://img.shields.io/github/stars/LlenRotse/ACC-Collab?style=social)](https://github.com/LlenRotse/ACC-Collab)

- **[2024-10-16]** [ICLR 2025] [Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance](https://openreview.net/forum?id=sRIU6k2TcU) [![GitHub stars](https://img.shields.io/github/stars/thunlp/ProactiveAgent?style=social)](https://github.com/thunlp/ProactiveAgent)

- **[2024-09-26]** [arXiv 2024] [AssistantX: An LLM-Powered Proactive Assistant in Collaborative Human-Populated Environment](https://arxiv.org/abs/2409.17655) [![GitHub stars](https://img.shields.io/github/stars/AssistantX-Agent/AssistantX?style=social)](https://github.com/AssistantX-Agent/AssistantX)

- **[2024-09-25]** [arXiv 2024] [AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents](https://arxiv.org/abs/2409.17140)

- **[2024-09-13]** [arXiv 2024] [Mutual Theory of Mind in Human-AI Collaboration: An Empirical Study with LLM-driven AI Agents in a Real-time Shared Workspace Task](https://arxiv.org/abs/2409.08811)

- **[2024-08-27]** [EMNLP 2024] [Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations](https://aclanthology.org/2024.emnlp-main.554/) [![GitHub stars](https://img.shields.io/github/stars/stanford-oval/storm?style=social)](https://github.com/stanford-oval/storm)

- **[2024-07-12]** [SME 2024] [Human-LLM collaboration in generative design for customization](https://www.sciencedirect.com/science/article/pii/S0278612525000731)

- **[2024-06-20]** [RAL 2024] [Enhancing the LLM-Based Robot Manipulation Through Human-Robot Collaboration](https://ieeexplore.ieee.org/document/10561501)

- **[2024-06-18]** [ICLR 2025] [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://openreview.net/forum?id=roNSXZpUDN) [![GitHub stars](https://img.shields.io/github/stars/sierra-research/tau-bench?style=social)](https://github.com/sierra-research/tau-bench)

- **[2024-06-17]** [EMNLP 2024] [Ask-before-Plan: Proactive Language Agents for Real-World Planning](https://aclanthology.org/2024.findings-emnlp.636/) [![GitHub stars](https://img.shields.io/github/stars/magicgh/Ask-before-Plan?style=social)](https://github.com/magicgh/Ask-before-Plan)

- **[2024-06-14]** [NeurIPS 2024] [DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning](https://proceedings.neurips.cc/paper_files/paper/2024/hash/1704ddd0bb89f159dfe609b32c889995-Abstract-Conference.html) [![GitHub stars](https://img.shields.io/github/stars/DigiRL-agent/digirl?style=social)](https://github.com/DigiRL-agent/digirl)

- **[2024-06-04]** [CASE 2024] [Enhancing Human-Robot Collaborative Assembly in Manufacturing Systems Using Large Language Models](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10711843)

- **[2024-05-30]** [arXiv 2024] [Safe Multi-agent Reinforcement Learning with Natural Language Constraints](https://arxiv.org/abs/2405.20018)

- **[2024-05-27]** [AAAI 2025] [REVECA: Adaptive Planning and Trajectory-based Validation in Cooperative Language Agents using Information Relevance and Relative Proximity](https://arxiv.org/abs/2405.16751)

- **[2024-04-23]** [NeurIPS 2024] [Aligning LLM Agents by Learning Latent Preference from User Edits](https://openreview.net/forum?id=DlYNGpCuwa) [![GitHub stars](https://img.shields.io/github/stars/gao-g/prelude?style=social)](https://github.com/gao-g/prelude)

- **[2024-04-18]** [arXiv 2024] [AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaboration](https://arxiv.org/abs/2404.11943) [![GitHub stars](https://img.shields.io/github/stars/AgentCoord/AgentCoord)](https://github.com/AgentCoord/AgentCoord)

- **[2024-04-05]** [IUI 2024] [PDFChatAnnotator: A Human-LLM Collaborative Multi-Modal Data Annotation Tool for PDF-Format Catalogs](https://dl.acm.org/doi/10.1145/3640543.3645174)

- **[2024-03-19]** [arXiv 2024] [Embodied LLM Agents Learn to Cooperate in Organized Teams](https://arxiv.org/abs/2403.12482) [![GitHub stars](https://img.shields.io/github/stars/tobeatraceur/Organized-LLM-Agents?style=social)](https://github.com/tobeatraceur/Organized-LLM-Agents)

- **[2024-02-08]** [arXiv 2024] [WebLINX: Real-World Website Navigation with Multi-Turn Dialogue](https://arxiv.org/abs/2402.05930) [![GitHub stars](https://img.shields.io/github/stars/McGill-NLP/WebLINX?style=social)](https://github.com/McGill-NLP/WebLINX)

- **[2024-02-07]** [NeurIPS 2024] [Can Large Language Model Agents Simulate Human Trust Behavior?](https://arxiv.org/abs/2402.04559) [![GitHub stars](https://img.shields.io/github/stars/camel-ai/agent-trust?style=social)](https://github.com/camel-ai/agent-trust)

- **[2024-01-25]** [arXiv 2024] [A2C: A Modular Multi-stage Collaborative Decision Framework for Human-AI Teams](https://arxiv.org/abs/2401.14432)

- **[2023-12-23]** [AAMAS 2024] [LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination](https://arxiv.org/abs/2312.15224)

- **[2023-10-18]** [ICLR 2024] [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://openreview.net/forum?id=mM7VurbA4r) [![GitHub stars](https://img.shields.io/github/stars/sotopia-lab/sotopia?style=social)](https://github.com/sotopia-lab/sotopia)

- **[2023-09-19]** [WACV 2024] [Drive as You Speak: Enabling Human-Like Interaction with Large Language Models in Autonomous Vehicles](https://arxiv.org/abs/2309.10228)

- **[2023-09-19]** [ICLR 2024] [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://arxiv.org/abs/2309.10691) [![GitHub stars](https://img.shields.io/github/stars/xingyaoww/mint-bench?style=social)](https://github.com/xingyaoww/mint-bench)

- **[2023-09-18]** [NAACL 2024] [MindAgent: Emergent Gaming Interaction](https://aclanthology.org/2024.findings-naacl.200/) [![GitHub stars](https://img.shields.io/github/stars/mindagent/mindagent?style=social)](https://github.com/mindagent/mindagent)

- **[2023-08-01]** [ICML 2023] [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://openreview.net/forum?id=VtmBAGCN7o) [![GitHub stars](https://img.shields.io/github/stars/FoundationAgents/MetaGPT?style=social)](https://github.com/FoundationAgents/MetaGPT)

- **[2023-07-05]** [ICLR 2024] [Building Cooperative Embodied Agents Modularly with Large Language Models](https://arxiv.org/abs/2307.02485)

- **[2023-07-04]** [ICML 2023] [Embodied Task Planning with Large Language Models](https://arxiv.org/abs/2307.01848) [![GitHub stars](https://img.shields.io/github/stars/Gary3410/TaPA?style=social)](https://github.com/Gary3410/TaPA)

- **[2023-06-01]** [IEEE 2023] [Improved Trust in Human-Robot Collaboration With ChatGPT](https://ieeexplore.ieee.org/abstract/document/10141597)

- **[2023-05-22]** [EACL 2024] [Investigating Agency of LLMs in Human-AI Collaboration Tasks](https://aclanthology.org/2024.eacl-long.119/)

- **[2023-04-21]** [EACL 2024] [Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback](https://arxiv.org/abs/2304.10750)

## 📚 Applications, Datasets & Benchmarks
 ([©️click here back to table of contents👆🏻](#contents))

### 💻 Web Navigation & Computer Use

- **[2026-02-19]** [arXiv 2026] [Modeling Distinct Human Interaction in Web Agents (CowCorpus)](https://arxiv.org/abs/2602.17588)

- **[2026-02-18]** [arXiv 2026] [Overseeing Agents Without Constant Oversight: Challenges and Opportunities](https://arxiv.org/abs/2602.16844)

### 👨🏻‍💻 Software Engineering, Coding

- **[2026-05-09]** [arXiv 2026] [AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators](https://arxiv.org/abs/2605.08647)

- **[2026-04-20]** [arXiv 2026] [CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks](https://arxiv.org/abs/2606.09833)

- **[2026-03-27]** [arXiv 2026] [Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents](https://arxiv.org/abs/2603.26233)

- **[2023-06-26]** [NeurIPS 2023] [InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback](https://arxiv.org/abs/2306.14898) [![GitHub stars](https://img.shields.io/github/stars/princeton-nlp/intercode?style=social)](https://github.com/princeton-nlp/intercode)

### 🤖 Embodied AI, Robotics

- **[2023-07-05]** [ICLR 2024] [Building Cooperative Embodied Agents Modularly with Large Language Models](https://arxiv.org/abs/2307.02485) [![GitHub stars](https://img.shields.io/github/stars/UMass-Embodied-AGI/CoELA?style=social)](https://github.com/UMass-Embodied-AGI/CoELA)

- **[2023-07-04]** [arXiv 2023] [Embodied Task Planning with Large Language Models](https://arxiv.org/abs/2307.01848) [![GitHub stars](https://img.shields.io/github/stars/Gary3410/TaPA?style=social)](https://github.com/Gary3410/TaPA)

- **[2023-04-21]** [EACL 2024 Findings] [Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback](https://arxiv.org/abs/2304.10750) [![GitHub stars](https://img.shields.io/github/stars/microsoft/iglu-datasets?style=social)](https://github.com/microsoft/iglu-datasets)

### 💬 Conversation System

- **[2026-06-17]** [arXiv 2026] [Learning User Simulators with Turing Rewards](https://arxiv.org/abs/2606.19336)

- **[2026-06-04]** [arXiv 2026] [Re-Centering Humans in LLM Personalization](https://arxiv.org/abs/2606.06614)

- **[2026-05-19]** [arXiv 2026] [Reinforcing Human Behavior Simulation via Verbal Feedback (DITTO & SOUL)](https://arxiv.org/abs/2605.20506)

- **[2026-01-10]** [arXiv 2026] [Value of Information: A Framework for Human-Agent Communication](https://arxiv.org/abs/2601.06407)

- **[2024-08-27]** [EMNLP 2024] [Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations](https://arxiv.org/abs/2408.15232) [![GitHub stars](https://img.shields.io/github/stars/stanford-oval/storm?style=social)](https://github.com/stanford-oval/storm)

### 📊 Data Science, Scientific Discovery

- **[2026-03-19]** [arXiv 2026] [AgentDS: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science](https://arxiv.org/abs/2603.19005) [[Project]](https://agentds.org/)

### 🎮 Gaming

- **[2026-06-04]** [ICML 2026] [CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement](https://arxiv.org/abs/2606.05793)

- **[2023-09-18]** [ICLR 2024] [MindAgent: Emergent Gaming Interaction](https://arxiv.org/abs/2309.09971) [![GitHub stars](https://img.shields.io/github/stars/mindagent/mindagent?style=social)](https://github.com/mindagent/mindagent)

### 💰 Finance

- **[2025-03-04]** [arXiv 2025] [FinArena: A Human-Agent Collaboration Framework for Financial Market Analysis and Forecasting](https://arxiv.org/abs/2503.02692) [Data Link](https://huggingface.co/datasets/Illogicaler/FinArena-low-cost-dataset)

### 🏥 Healthcare, Medicine

- **[2026-05-27]** [FAccT 2026] [Not All Uncertainty Is Equal: How Uncertainty Granularity Shapes Human Verification in LLM-Assisted Decision Making](https://arxiv.org/abs/2605.28571)

### 🧩 General-Purpose Assistants, Cross-Domain

- **[2026-07-18]** [arXiv 2026] [Just A Rather Very Intelligent Spoken Agent (JarvisBench)](https://arxiv.org/abs/2607.16610) [[Project]](https://cchen1436.github.io/jarvis)

- **[2026-07-05]** [arXiv 2026] [HAS-Bench: Evaluating LLM-Based Human-Agent Systems under Configurable Human Participation](https://arxiv.org/abs/2607.04329)

- **[2026-06-17]** [arXiv 2026] [Uncertainty Decomposition for Clarification Seeking in LLM Agents](https://arxiv.org/abs/2606.19559)

- **[2026-06-02]** [arXiv 2026] [Uncertainty-Aware Clarification in LLM Agents with Information Gain](https://arxiv.org/abs/2606.03135)

- **[2026-05-23]** [arXiv 2026] [Reframing LLM Agent Security as an Agent-Human Interaction Problem](https://arxiv.org/abs/2605.24309)

- **[2026-04-24]** [arXiv 2026] [A Decoupled Human-in-the-Loop System for Controlled Autonomy in Agentic Workflows](https://arxiv.org/abs/2604.23049)

- **[2026-04-07]** [arXiv 2026] [Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge](https://arxiv.org/abs/2604.05593)

### 🛍️ Retail, Telecom
<a name="-retail-telecom"></a>

- **[2026-05-08]** [arXiv 2026] [SalesSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators](https://arxiv.org/abs/2605.08334)

### 🛩️ Travel
<a name="-travel"></a>

### ✍️ Writing

- **[2026-05-11]** [arXiv 2026] [ECHO: Explainable Co-editing with Human-in-the-loop Operations for Presentation Refinement](https://arxiv.org/abs/2606.09851)

- **[2026-03-02]** [arXiv 2026] [ViviDoc: Generating Interactive Documents through Human-Agent Collaboration](https://arxiv.org/abs/2603.01912) [![GitHub stars](https://img.shields.io/github/stars/MisterBrookT/vividoc?style=social)](https://github.com/MisterBrookT/vividoc)

- **[2026-01-01]** [arXiv 2026] [Progressive Ideation using an Agentic AI Framework for Human-AI Co-Creation (MIDAS)](https://arxiv.org/abs/2601.00475)

For a detailed introduction of the taxonomy, please refer to Section 3 in our survey paper: [LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey](https://arxiv.org/pdf/2505.00753).

![image](https://raw.githubusercontent.com/HenryPengZou/Awesome-Human-Agent-Collaboration-Interaction-Systems/main/images/taxonomy.png)

---

### 🤝 Human Feedback

***Human Feedback*** can occur during ***different phases*** in ***various types*** and ***granularities***. In the following table, we summarize different dimensions of Human Feedback in LLM-based human-agent systems, including feedback type, granularity, and phase. For each dimension, a summary, key characteristics, and example works are provided for comparison. More details are in [Section 3.2 of our survey paper](https://arxiv.org/pdf/2505.00753).

![image](https://raw.githubusercontent.com/HenryPengZou/Awesome-Human-Agent-Collaboration-Interaction-Systems/main/images/human_feedback.png)

| Title | Date & Code | Feedback Type | Feedback Subtype | Feedback Granularity | Feedback Phase |
| --- | :---: | :---: | :---: | :---: | :---: |
| [Just A Rather Very Intelligent Spoken Agent (JarvisBench)](https://arxiv.org/abs/2607.16610) | [2026/07](https://cchen1436.github.io/jarvis) | Guidance, Corrective | Refinement, Critique | Segment | During Task |
| [LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability](https://arxiv.org/abs/2607.06157) | [2026/07](https://github.com/wcx21/deliberative-collaboration-agents) [![GitHub stars](https://img.shields.io/github/stars/wcx21/deliberative-collaboration-agents?style=social)](https://github.com/wcx21/deliberative-collaboration-agents) | Guidance, Evaluative | Critique, Binary Assessment | Segment | During Task |
| [HAS-Bench: Evaluating LLM-Based Human-Agent Systems under Configurable Human Participation](https://arxiv.org/abs/2607.04329) | [2026/07](https://arxiv.org/abs/2607.04329) | Guidance, Evaluative, Corrective, Implicit | Critique, Refinement, Binary Assessment, Human Control | Holistic, Segment | Initial Setup, During Task, Post Task |
| [Uncertainty Decomposition for Clarification Seeking in LLM Agents](https://arxiv.org/abs/2606.19559) | [2026/06](https://arxiv.org/abs/2606.19559) | Guidance | Demonstration | Segment | During Task |
| [Learning User Simulators with Turing Rewards](https://arxiv.org/abs/2606.19336) | [2026/06](https://arxiv.org/abs/2606.19336) | Implicit | User Action | Segment | During Task |
| [Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents (TRACE)](https://arxiv.org/abs/2606.13174) | [2026/06](https://github.com/YujunZhou/tellonce) [![GitHub stars](https://img.shields.io/github/stars/YujunZhou/tellonce?style=social)](https://github.com/YujunZhou/tellonce) | Corrective, Guidance | Refinement, Critique | Segment | During Task, Post Task |
| [Re-Centering Humans in LLM Personalization](https://arxiv.org/abs/2606.06614) | [2026/06](https://arxiv.org/abs/2606.06614) | Evaluative, Implicit | Preference Ranking, Scalar Rating, User Action | Holistic, Segment | Post Task |
| [CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement](https://arxiv.org/abs/2606.05793) | [2026/06](https://arxiv.org/abs/2606.05793) | Implicit, Guidance | User Action, Critique | Segment | During Task |
| [Human Oversight of Agentic Systems in Practice: Examining the Oversight Work, Challenges, and Heuristics of Developers Using Software Agents](https://arxiv.org/abs/2606.05391) | [2026/06](https://arxiv.org/abs/2606.05391) | Evaluative, Corrective, Guidance | Binary Assessment, Refinement, Critique | Holistic, Segment | Initial Setup, During Task, Post Task |
| [Uncertainty-Aware Clarification in LLM Agents with Information Gain](https://arxiv.org/abs/2606.03135) | [2026/06](https://arxiv.org/abs/2606.03135) | Guidance | Demonstration | Segment | During Task |
| [Not All Uncertainty Is Equal: How Uncertainty Granularity Shapes Human Verification in LLM-Assisted Decision Making](https://arxiv.org/abs/2605.28571) | [2026/05](https://arxiv.org/abs/2605.28571) | Evaluative, Implicit | Binary Assessment, User Action | Segment, Holistic | During Task |
| [VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions](https://arxiv.org/abs/2605.27141) | [2026/05](https://github.com/meituan-longcat/VitaBench-2.0) [![GitHub stars](https://img.shields.io/github/stars/meituan-longcat/VitaBench-2.0?style=social)](https://github.com/meituan-longcat/VitaBench-2.0) | Implicit, Guidance | User Action, Demonstration | Segment | Initial Setup, During Task |
| [Reinforcing Human Behavior Simulation via Verbal Feedback (DITTO & SOUL)](https://arxiv.org/abs/2605.20506) | [2026/05](https://arxiv.org/abs/2605.20506) | Guidance, Corrective | Critique, Refinement | Holistic, Segment | Post Task |
| [ECHO: Explainable Co-editing with Human-in-the-loop Operations for Presentation Refinement](https://arxiv.org/abs/2606.09851) | [2026/05](https://arxiv.org/abs/2606.09851) | Corrective, Guidance | Refinement, Demonstration | Segment | During Task |
| [AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators](https://arxiv.org/abs/2605.08647) | [2026/05](https://arxiv.org/abs/2605.08647) | Guidance, Evaluative | Critique, Binary Assessment | Segment | Initial Setup, During Task |
| [SalesSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators](https://arxiv.org/abs/2605.08334) | [2026/05](https://arxiv.org/abs/2605.08334) | Implicit, Guidance | User Action, Critique | Segment | During Task |
| [A Decoupled Human-in-the-Loop System for Controlled Autonomy in Agentic Workflows](https://arxiv.org/abs/2604.23049) | [2026/04](https://arxiv.org/abs/2604.23049) | Evaluative, Corrective, Implicit | Binary Assessment, Refinement, Human Control | Segment | Initial Setup, During Task |
| [CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks](https://arxiv.org/abs/2606.09833) | [2026/04](https://arxiv.org/abs/2606.09833) | Guidance, Evaluative, Implicit | Demonstration, Scalar Rating, User Action | Holistic, Segment | During Task, Post Task |
| [When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation (InterruptBench)](https://arxiv.org/abs/2604.00892) | [2026/04](https://github.com/HenryPengZou/InterruptBench) [![GitHub stars](https://img.shields.io/github/stars/HenryPengZou/InterruptBench?style=social)](https://github.com/HenryPengZou/InterruptBench) | Corrective, Guidance | Refinement, Critique | Segment | During Task |
| [Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents](https://arxiv.org/abs/2603.26233) | [2026/03](https://arxiv.org/abs/2603.26233) | Guidance | Demonstration, Critique | Segment | During Task |
| [User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction (VARS)](https://arxiv.org/abs/2603.20939) | [2026/03](https://github.com/YurenHao0426/VARS) [![GitHub stars](https://img.shields.io/github/stars/YurenHao0426/VARS?style=social)](https://github.com/YurenHao0426/VARS) | Evaluative, Implicit | Scalar Rating, User Action | Segment | During Task, Post Task |
| [LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks](https://arxiv.org/abs/2604.13072) | [2026/03](https://github.com/Mosi-AI/LiveClawBench) [![GitHub stars](https://img.shields.io/github/stars/Mosi-AI/LiveClawBench?style=social)](https://github.com/Mosi-AI/LiveClawBench) | Implicit, Guidance | User Action, Demonstration | Segment | Initial Setup, During Task |
| [AgentDS: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science](https://arxiv.org/abs/2603.19005) | [2026/03](https://agentds.org/) | Guidance, Corrective, Evaluative | Demonstration, Refinement, Scalar Rating | Holistic, Segment | Initial Setup, During Task, Post Task |
| [ViviDoc: Generating Interactive Documents through Human-Agent Collaboration](https://arxiv.org/abs/2603.01912) | [2026/03](https://github.com/MisterBrookT/vividoc) [![GitHub stars](https://img.shields.io/github/stars/MisterBrookT/vividoc?style=social)](https://github.com/MisterBrookT/vividoc) | Corrective, Guidance | Refinement, Demonstration | Segment | During Task |
| [InfoPO: Information-Driven Policy Optimization for User-Centric Agents](https://arxiv.org/abs/2603.00656) | [2026/02](https://github.com/kfq20/InfoPO) [![GitHub stars](https://img.shields.io/github/stars/kfq20/InfoPO?style=social)](https://github.com/kfq20/InfoPO) | Guidance, Implicit | Demonstration, User Action | Segment | During Task |
| [Modeling Distinct Human Interaction in Web Agents (CowCorpus)](https://arxiv.org/abs/2602.17588) | [2026/02](https://arxiv.org/abs/2602.17588) | Implicit, Corrective | User Action, Human Control, Refinement | Segment | During Task |
| [Overseeing Agents Without Constant Oversight: Challenges and Opportunities](https://arxiv.org/abs/2602.16844) | [2026/02](https://arxiv.org/abs/2602.16844) | Evaluative, Corrective | Binary Assessment, Critique | Segment, Holistic | During Task, Post Task |
| [Learning Personalized Agents from Human Feedback](https://arxiv.org/abs/2602.16173) | [2026/02](https://github.com/facebookresearch/PAHF) [![GitHub stars](https://img.shields.io/github/stars/facebookresearch/PAHF?style=social)](https://github.com/facebookresearch/PAHF) | Guidance, Corrective, Evaluative | Critique, Refinement, Preference Ranking | Segment | Initial Setup, During Task, Post Task |
| [Value of Information: A Framework for Human-Agent Communication](https://arxiv.org/abs/2601.06407) | [2026/01](https://arxiv.org/abs/2601.06407) | Guidance | Demonstration | Segment | During Task |
| [Progressive Ideation using an Agentic AI Framework for Human-AI Co-Creation (MIDAS)](https://arxiv.org/abs/2601.00475) | [2026/01](https://arxiv.org/abs/2601.00475) | Evaluative, Guidance | Preference Ranking, Critique | Segment | During Task |
| [From Correctness to Collaboration: Toward a Human-Centered Framework for Evaluating AI Agent Behavior in Software Engineering](https://arxiv.org/abs/2512.23844) | [2025/12](https://arxiv.org/abs/2512.23844) | Guidance, Evaluative | Critique, Preference Ranking | Segment | Initial Setup, During Task |
| [CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding](https://arxiv.org/abs/2512.04111) | [2025/11](https://arxiv.org/abs/2512.04111) | Guidance, Corrective | Refinements, Critique | Segment, Holistic | During Task |
| [Training Proactive and Personalized LLM Agents](https://arxiv.org/abs/2511.02208) | [2025/11](https://github.com/sunnweiwei/PPP-Agent) [![GitHub stars](https://img.shields.io/github/stars/sunnweiwei/PPP-Agent?style=social)](https://github.com/sunnweiwei/PPP-Agent) | Guidance, Evaluative | Scalar Rating, Refinements | Segment, Holistic | During Task |
| [Training LLM Agents to Empower Humans](https://arxiv.org/abs/2510.13709) | [2025/10](https://github.com/festusev/codegen_empowerment) [![GitHub stars](https://img.shields.io/github/stars/festusev/codegen_empowerment?style=social)](https://github.com/festusev/codegen_empowerment) | Implicit, Corrective | User Action, Refinements | Segment | During Task |
| [How can we assess human-agent interactions? Case studies in software agent design](https://arxiv.org/abs/2510.09801v2) | [2025/10](https://arxiv.org/abs/2510.09801v2) | Evaluative | Scalar Rating | Segment | During Task |
| [RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback](https://arxiv.org/abs/2510.06186) | [2025/10](https://github.com/ChunyuMiao98/RECODE-H) [![GitHub stars](https://img.shields.io/github/stars/ChunyuMiao98/RECODE-H?style=social)](https://github.com/ChunyuMiao98/RECODE-H) | Guidance, Corrective | Refinements, Critique, Demonstration | Segment | During Task |
| [UserRL: Training Proactive User-Centric Agent via Reinforcement Learning](https://arxiv.org/abs/2509.19736) | [2025/09](https://github.com/SalesforceAIResearch/UserRL) [![GitHub stars](https://img.shields.io/github/stars/SalesforceAIResearch/UserRL?style=social)](https://github.com/SalesforceAIResearch/UserRL) | Evaluative, Guidance, Implicit | Scalar Rating, Refinements, Critique | Segment | During Task |
| [MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use](https://arxiv.org/abs/2508.18669) | [2025/08](https://github.com/zzwkk/MUA-RL) [![GitHub stars](https://img.shields.io/github/stars/zzwkk/MUA-RL?style=social)](https://github.com/zzwkk/MUA-RL) | Evaluative, Guidance | Binary Assessment, Refinement | Holistic | Initial Setup, During Task |
| [Magentic-UI: Towards Human-in-the-loop Agentic Systems](https://www.arxiv.org/abs/2507.22358) | [2025/07](https://github.com/microsoft/magentic-ui) [![GitHub stars](https://img.shields.io/github/stars/microsoft/magentic-ui?style=social)](https://github.com/microsoft/magentic-ui) | Evaluative, Corrective, Guidance, Implicit | Binary Assessment, Refinement, Critique, User Action | Segment | During Task, Post Task |
| [UserBench: An Interactive Gym Environment for User-Centric Agents](https://arxiv.org/abs/2507.22034) | [2025/07](https://github.com/SalesforceAIResearch/UserBench) [![GitHub stars](https://img.shields.io/github/stars/SalesforceAIResearch/UserBench?style=social)](https://github.com/SalesforceAIResearch/UserBench) | Implicit, Guidance | User Action, Refinement | Segment | Initial Setup, During Task |
| [Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance](https://www.arxiv.org/abs/2507.17131) | [2025/07](https://github.com/yf-he/aria) [![GitHub stars](https://img.shields.io/github/stars/yf-he/aria?style=social)](https://github.com/yf-he/aria) | Corrective, Guidance | Refinement, Critique | Segment | During Task |
| [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://arxiv.org/abs/2506.07982) | [2025/06](https://github.com/sierra-research/tau2-bench) [![GitHub stars](https://img.shields.io/github/stars/sierra-research/tau2-bench?style=social)](https://github.com/sierra-research/tau2-bench) | Evaluative, Implicit | Binary Assessment, User Action | Segment, Holistic | Initial Setup, During Task |
| [Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training](https://arxiv.org/abs/2406.00222) | [2025/05](https://github.com/google-research/google-research/tree/master/learning_to_clarify) | Corrective | Refinement | Segment | During Task |
| [Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild](https://arxiv.org/abs/2505.16023) | [2025/05](https://github.com/microsoft/prototypical-hai-collaborations) [![GitHub stars](https://img.shields.io/github/stars/microsoft/prototypical-hai-collaborations?style=social)](https://github.com/microsoft/prototypical-hai-collaborations) | Corrective, Guidance, Evaluative | Refinement, Binary Assessment, Demonstration | Segment, Holistic | During Task |
| [XtraGPT: LLMs for Human-AI Collaboration on Controllable Academic Paper Revision](https://arxiv.org/abs/2505.11336) | [2025/05](https://github.com/NuoJohnChen/XtraGPT) [![GitHub stars](https://img.shields.io/github/stars/NuoJohnChen/XtraGPT?style=social)](https://github.com/NuoJohnChen/XtraGPT) | Guidance, Evaluative | Critique, Preference Ranking | Segment | Initial Setup, Post Task |
| [MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft](https://arxiv.org/abs/2504.08388) | [2025/04](https://github.com/microsoft/MineWorld) [![GitHub stars](https://img.shields.io/github/stars/microsoft/MineWorld?style=social)](https://github.com/microsoft/MineWorld) | Evaluative | Scalar Rating | Holistic | Post Task |
| [Experimental Exploration: Investigating Cooperative Interaction Behavior Between Humans and Large Language Model Agents](https://arxiv.org/abs/2503.07320) | [2025/03](https://arxiv.org/abs/2503.07320) | Implicit | User Action | Segment | During Task |
| [SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks](https://arxiv.org/abs/2503.15478) | [2025/03](https://github.com/facebookresearch/sweet_rl) [![GitHub stars](https://img.shields.io/github/stars/facebookresearch/sweet_rl?style=social)](https://github.com/facebookresearch/sweet_rl) | Corrective, Implicit | Refinement, User Action | Segment | During Task |
| [FinArena: A Human-Agent Collaboration Framework for Financial Market Analysis and Forecasting](https://arxiv.org/abs/2503.02692) | [2025/03](https://huggingface.co/datasets/Illogicaler/FinArena-low-cost-dataset) | Guidance | Demonstration | Segment | During Task |
| [Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration](https://arxiv.org/abs/2502.11882) | [2025/02](https://github.com/sjtu-marl/DPT-Agent) [![GitHub stars](https://img.shields.io/github/stars/sjtu-marl/DPT-Agent?style=social)](https://github.com/sjtu-marl/DPT-Agent) | Guidance | Critique | Holistic | During Task |
| [ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments](https://arxiv.org/abs/2502.19852) | [2025/02](https://github.com/stovecat/convcodeworld) [![GitHub stars](https://img.shields.io/github/stars/stovecat/convcodeworld?style=social)](https://github.com/stovecat/convcodeworld) | Guidance  | Demonstration, Critique | Segment | During Task |
| [CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigation](https://arxiv.org/abs/2501.16609) | [2025/01](https://oaishi.github.io/cowpilot.html) | Corrective, Implicit | User Action, Refinement | Segment | During Task |
| [Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration (Co-Gym)](https://arxiv.org/abs/2412.15701) | [2024/12](https://github.com/SALT-NLP/collaborative-gym) [![GitHub stars](https://img.shields.io/github/stars/SALT-NLP/collaborative-gym?style=social)](https://github.com/SALT-NLP/collaborative-gym) | Corrective | Refinement | Segment | During Task |
| [Towards Modeling Human-Agentic Collaborative Workflows: A BPMN Extension](https://arxiv.org/abs/2412.05958) | [2024/12](https://github.com/BESSER-PEARL/agentic-bpmn) [![GitHub stars](https://img.shields.io/github/stars/BESSER-PEARL/agentic-bpmn?style=social)](https://github.com/BESSER-PEARL/agentic-bpmn) | Guidance | Demonstration | Holistic | Initial Setup, During Task, Post Task |
| [To Help or Not to Help: LLM-based Attentive Support for Human-Robot Group Interactions](https://ieeexplore.ieee.org/abstract/document/10801517) | [2024/10](https://github.com/HRI-EU/AttentiveSupport) [![GitHub stars](https://img.shields.io/github/stars/HRI-EU/AttentiveSupport?style=social)](https://github.com/HRI-EU/AttentiveSupport) | Implicit, Guidance | Demonstration, User Action | Holistic | Initial Setup, During Task |
| [PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks](https://openreview.net/forum?id=T5QLRRHyL1) | [2024/10](https://github.com/facebookresearch/partnr-planner/tree/main/) [![GitHub stars](https://img.shields.io/github/stars/facebookresearch/partnr-planner?style=social)](https://github.com/facebookresearch/partnr-planner/tree/main/) | Corrective, Guidance | Refinement, Critique | Holistic, Segment | During Task, Post Task |
| [AssistantX: An LLM-Powered Proactive Assistant in Collaborative Human-Populated Environment](https://arxiv.org/abs/2409.17655) | [2024/09](https://github.com/AssistantX-Agent/AssistantX) [![GitHub stars](https://img.shields.io/github/stars/AssistantX-Agent/AssistantX?style=social)](https://github.com/AssistantX-Agent/AssistantX) | Implicit | Human Control | Holistic | Initial Setup |
| [Mutual Theory of Mind in Human-AI Collaboration: An Empirical Study with LLM-driven AI Agents in a Real-time Shared Workspace Task](https://arxiv.org/abs/2409.08811) | [2024/09](https://arxiv.org/abs/2409.08811) | Corrective | Refinement | Segment | During Task |
| [Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations](https://arxiv.org/abs/2408.15232) | [2024/08](https://github.com/stanford-oval/storm) [![GitHub stars](https://img.shields.io/github/stars/stanford-oval/storm?style=social)](https://github.com/stanford-oval/storm) | Guidance | Demonstration | Segment | During Task |
| [Human-LLM collaboration in generative design for customization](https://www.sciencedirect.com/science/article/abs/pii/S0278612525000731) | [2024/07](https://www.sciencedirect.com/science/article/abs/pii/S0278612525000731) | Guidance, Evaluative | Demonstration, Binary Assessment, Preference Ranking | Holistic, Segment | Initial Setup, Post Task |
| [WebCanvas: Benchmarking Web Agents in Online Environments](https://arxiv.org/pdf/2406.12373) | [2024/06](https://huggingface.co/datasets/iMeanAI/Mind2Web-Live) | Evaluative | Scalar Rating | Holistic | Post Task |
| [Enhancing Human-Robot Collaborative Assembly in Manufacturing Systems Using Large Language Models](https://arxiv.org/abs/2406.01915) | [2024/06](https://arxiv.org/abs/2406.01915) | Corrective, Guidance | Demonstration, Refinement, Critique | Segment | Initial Setup, During Task |
| [Enhancing the LLM-Based Robot Manipulation Through Human-Robot Collaboration](https://ieeexplore.ieee.org/abstract/document/10561501) | [2024/06](https://ieeexplore.ieee.org/abstract/document/10561501) | Corrective | Refinement | Holistic | During Task |
| [DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning](https://arxiv.org/abs/2406.11896) | [2024/06](https://github.com/DigiRL-agent/digirl) [![GitHub stars](https://img.shields.io/github/stars/DigiRL-agent/digirl?style=social)](https://github.com/DigiRL-agent/digirl) | Evaluative | Binary Assessment | Holistic | During Task, Post Task |
| [REVECA: Adaptive Planning and Trajectory-based Validation in Cooperative Language Agents using Information Relevance and Relative Proximity](https://arxiv.org/abs/2405.16751) | [2024/05](https://arxiv.org/abs/2405.16751) | Implicit | Human Control | Segment | During Task |
| [Autonomous Evaluation and Refinement of Digital Agents](https://arxiv.org/abs/2404.06474) | [2024/04](https://github.com/Berkeley-NLP/Agent-Eval-Refine) [![GitHub stars](https://img.shields.io/github/stars/Berkeley-NLP/Agent-Eval-Refine?style=social)](https://github.com/Berkeley-NLP/Agent-Eval-Refine) | Evaluative | Binary Assessment | Holistic | Post Task |
| [A Human-Computer Collaborative Tool for Training a Single Large Language Model Agent into a Network through Few Examples](https://arxiv.org/abs/2404.15974) | [2024/04](https://arxiv.org/abs/2404.15974) | Corrective, Guidance | Demonstration, Refinement | Segment | During Task |
| [An LLM-based approach for Enabling Seamless Human-Robot Collaboration in Assembly](https://www.sciencedirect.com/science/article/pii/S000785062400012X) | [2024/04](https://www.sciencedirect.com/science/article/pii/S000785062400012X) | Guidance, Corrective | Demonstration, Refinement | Segment | During Task |
| [AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaboration](https://arxiv.org/abs/2404.11943) | [2024/04](https://github.com/AgentCoord/AgentCoord) [![GitHub stars](https://img.shields.io/github/stars/AgentCoord/AgentCoord?style=social)](https://github.com/AgentCoord/AgentCoord) | Guidance, Corrective | Demonstration, Refinement | Segment | Initial Setup |
| [PDFChatAnnotator: A Human-LLM Collaborative Multi-Modal Data Annotation Tool for PDF-Format Catalogs](https://dl.acm.org/doi/abs/10.1145/3640543.3645174) | [2024/04](https://dl.acm.org/doi/abs/10.1145/3640543.3645174) | Corrective, Guidance | Demonstration, Refinement | Segment | During Task |
| [Embodied LLM Agents Learn to Cooperate in Organized Teams](https://arxiv.org/abs/2403.12482) | [2024/03](https://github.com/tobeatraceur/Organized-LLM-Agents) [![GitHub stars](https://img.shields.io/github/stars/tobeatraceur/Organized-LLM-Agents?style=social)](https://github.com/tobeatraceur/Organized-LLM-Agents) | Guidance  | Critique | Holistic | During Task | 
| [Large Language Model-based Human-Agent Collaboration for Complex Task Solving](https://arxiv.org/abs/2402.12914) | [2024/02](https://github.com/XueyangFeng/ReHAC) [![GitHub stars](https://img.shields.io/github/stars/XueyangFeng/ReHAC?style=social)](https://github.com/XueyangFeng/ReHAC) | Implicit  | Human Control  | Segment | During Task |
| [WebLINX: Real-World Website Navigation with Multi-Turn Dialogue](https://arxiv.org/abs/2402.05930) | [2024/02](https://github.com/McGill-NLP/WebLINX) [![GitHub stars](https://img.shields.io/github/stars/McGill-NLP/WebLINX?style=social)](https://github.com/McGill-NLP/WebLINX) | Guidance  | Demonstration | Holistic, Segment | During Task |
| [Ask-before-Plan: Proactive Language Agents for Real-World Planning](https://arxiv.org/abs/2406.12639) | [2024/01](https://github.com/magicgh/Ask-before-Plan) [![GitHub stars](https://img.shields.io/github/stars/magicgh/Ask-before-Plan?style=social)](https://github.com/magicgh/Ask-before-Plan) | Guidance | Demonstration, Critique | Segment | During Task |
| [A2C: A Modular Multi-stage Collaborative Decision Framework for Human-AI Teams](https://arxiv.org/abs/2401.14432) | [2024/01](https://anonymous.4open.science/r/A2C/README.md) | Guidance, Implicit, Corrective, Evaluative | Refinement, Binary Assessment, Critique, Human Control | Holistic, Segment | During Task |
| [LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination](https://arxiv.org/abs/2312.15224) | [2023/12](https://github.com/HosnLS/Hierarchical-Language-Agent) [![GitHub stars](https://img.shields.io/github/stars/HosnLS/Hierarchical-Language-Agent?style=social)](https://github.com/HosnLS/Hierarchical-Language-Agent) | Guidance, Corrective | Demonstration, Refinement | Segment | During Task |
| [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://arxiv.org/abs/2310.11667) | [2023/10](https://arxiv.org/abs/2310.11667) | Evaluative, Implicit | Scalar Rating, User Action | Holistic, Segment | During Task, Post Task |
| [MindAgent: Emergent Gaming Interaction](https://arxiv.org/abs/2309.09971) | [2023/09](https://github.com/mindagent/mindagent) [![GitHub stars](https://img.shields.io/github/stars/mindagent/mindagent?style=social)](https://github.com/mindagent/mindagent) | Corrective | Refinement | Segment | During Task |
| [Drive As You Speak: Enabling Human-Like Interaction With Large Language Models in Autonomous Vehicles](https://arxiv.org/abs/2309.10228) | [2023/09](https://arxiv.org/abs/2309.10228) | Guidance | Demonstration | Segment | During Task |
| [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://arxiv.org/pdf/2309.10691) | [2023/09](https://xwang.dev/mint-bench/) | Evaluative | Binary Assessment | Holistic | During Task |
| [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://arxiv.org/abs/2308.00352) | [2023/08](https://github.com/geekan/MetaGPT) [![GitHub stars](https://img.shields.io/github/stars/geekan/MetaGPT?style=social)](https://github.com/geekan/MetaGPT) | Evaluative, Guidance | Binary Assessment | Holistic | Initial Setup, Post Task |
| [LLM-Based Human-Robot Collaboration Framework for Manipulation Tasks](https://arxiv.org/abs/2308.14972) | [2023/08](https://arxiv.org/abs/2308.14972) | Corrective, Guidance | Demonstration, Refinement | Segment | During Task |
| [Embodied Task Planning with Large Language Models](https://arxiv.org/abs/2307.01848) | [2023/07](https://github.com/Gary3410/TaPA) [![GitHub stars](https://img.shields.io/github/stars/Gary3410/TaPA?style=social)](https://github.com/Gary3410/TaPA) | Guidance, Evaluative | Demonstration, Binary Assessment | Holistic, Segment | Initial Setup, Post Task |
| [Building cooperative embodied agents modularly with large language models](https://arxiv.org/abs/2307.02485) | [2023/07](https://arxiv.org/abs/2307.02485) | Evaluative | Scalar Rating | Holistic | Post Task |
| [Improved Trust in Human-Robot Collaboration With ChatGPT](https://ieeexplore.ieee.org/abstract/document/10141597) | [2023/06](https://ieeexplore.ieee.org/abstract/document/10141597) | Guidance | Demonstration, Critique | Segment | During Task |
| [Investigating Agency of LLMs in Human-AI Collaboration Tasks](https://arxiv.org/abs/2305.12815) | [2023/05](https://arxiv.org/abs/2305.12815) | Guidance | Demonstration, Critique | Segment | During Task |
| [Improving grounded language understanding in a collaborative environment by interacting with agents through help feedback](https://arxiv.org/abs/2304.10750) | [2023/04](https://arxiv.org/abs/2304.10750) | Corrective, Guidance | Demonstration, Refinement | Holistic | During Task |
| [PaLM-E: An Embodied Multimodal Language Model](https://openreview.net/forum?id=VTpHpqM3Cf&utm_campaign=The%20Batch&utm_source=hs_email&utm_medium=email&utm_content=284568789&_hsenc=p2ANqtz-9lsSL4nXMrOGBQqGoqktY5Yno_r9-nTOARZinDcgihFNqcOFEQb_MVtHKdpgI2AC3N8SrNW5PxcD0uxl4WeKcPJgUOgw) | [2023/03](https://palm-e.github.io) | Guidance, Implicit | Demonstration, User Action | Segment | During Task |
| [Ai chains: Transparent and controllable human-ai interaction by chaining large language model prompts](https://dl.acm.org/doi/abs/10.1145/3491102.3517582) | [2021/10](https://dl.acm.org/doi/abs/10.1145/3491102.3517582) | Corrective | Refinement | Segment | During Task |

---

| Title | Date & Code | Interaction Types | Interaction Variant |
| --- | :---: | :---: | :---: |
| [Just A Rather Very Intelligent Spoken Agent (JarvisBench)](https://arxiv.org/abs/2607.16610) | [2026/07](https://cchen1436.github.io/jarvis) | Collaboration | Supervision, Cooperation |
| [LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability](https://arxiv.org/abs/2607.06157) | [2026/07](https://github.com/wcx21/deliberative-collaboration-agents) [![GitHub stars](https://img.shields.io/github/stars/wcx21/deliberative-collaboration-agents?style=social)](https://github.com/wcx21/deliberative-collaboration-agents) | Collaboration | Cooperation, Coordination |
| [HAS-Bench: Evaluating LLM-Based Human-Agent Systems under Configurable Human Participation](https://arxiv.org/abs/2607.04329) | [2026/07](https://arxiv.org/abs/2607.04329) | Collaboration | Supervision, Delegation, Coordination |
| [Uncertainty Decomposition for Clarification Seeking in LLM Agents](https://arxiv.org/abs/2606.19559) | [2026/06](https://arxiv.org/abs/2606.19559) | Collaboration | Cooperation |
| [Learning User Simulators with Turing Rewards](https://arxiv.org/abs/2606.19336) | [2026/06](https://arxiv.org/abs/2606.19336) | Collaboration | Cooperation |
| [Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents (TRACE)](https://arxiv.org/abs/2606.13174) | [2026/06](https://github.com/YujunZhou/tellonce) [![GitHub stars](https://img.shields.io/github/stars/YujunZhou/tellonce?style=social)](https://github.com/YujunZhou/tellonce) | Collaboration | Supervision, Cooperation |
| [Re-Centering Humans in LLM Personalization](https://arxiv.org/abs/2606.06614) | [2026/06](https://arxiv.org/abs/2606.06614) | Collaboration | Cooperation |
| [CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement](https://arxiv.org/abs/2606.05793) | [2026/06](https://arxiv.org/abs/2606.05793) | Collaboration | Cooperation, Coordination |
| [Human Oversight of Agentic Systems in Practice: Examining the Oversight Work, Challenges, and Heuristics of Developers Using Software Agents](https://arxiv.org/abs/2606.05391) | [2026/06](https://arxiv.org/abs/2606.05391) | Collaboration | Supervision, Delegation |
| [Uncertainty-Aware Clarification in LLM Agents with Information Gain](https://arxiv.org/abs/2606.03135) | [2026/06](https://arxiv.org/abs/2606.03135) | Collaboration | Cooperation |
| [Not All Uncertainty Is Equal: How Uncertainty Granularity Shapes Human Verification in LLM-Assisted Decision Making](https://arxiv.org/abs/2605.28571) | [2026/05](https://arxiv.org/abs/2605.28571) | Collaboration | Supervision |
| [VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions](https://arxiv.org/abs/2605.27141) | [2026/05](https://github.com/meituan-longcat/VitaBench-2.0) [![GitHub stars](https://img.shields.io/github/stars/meituan-longcat/VitaBench-2.0?style=social)](https://github.com/meituan-longcat/VitaBench-2.0) | Collaboration | Cooperation, Delegation |
| [Reinforcing Human Behavior Simulation via Verbal Feedback (DITTO & SOUL)](https://arxiv.org/abs/2605.20506) | [2026/05](https://arxiv.org/abs/2605.20506) | Collaboration | Cooperation |
| [ECHO: Explainable Co-editing with Human-in-the-loop Operations for Presentation Refinement](https://arxiv.org/abs/2606.09851) | [2026/05](https://arxiv.org/abs/2606.09851) | Collaboration | Supervision, Cooperation |
| [AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators](https://arxiv.org/abs/2605.08647) | [2026/05](https://arxiv.org/abs/2605.08647) | Collaboration | Coordination |
| [SalesSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators](https://arxiv.org/abs/2605.08334) | [2026/05](https://arxiv.org/abs/2605.08334) | Collaboration | Cooperation |
| [A Decoupled Human-in-the-Loop System for Controlled Autonomy in Agentic Workflows](https://arxiv.org/abs/2604.23049) | [2026/04](https://arxiv.org/abs/2604.23049) | Collaboration | Supervision, Delegation |
| [CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks](https://arxiv.org/abs/2606.09833) | [2026/04](https://arxiv.org/abs/2606.09833) | Collaboration | Cooperation, Delegation |
| [When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation (InterruptBench)](https://arxiv.org/abs/2604.00892) | [2026/04](https://github.com/HenryPengZou/InterruptBench) [![GitHub stars](https://img.shields.io/github/stars/HenryPengZou/InterruptBench?style=social)](https://github.com/HenryPengZou/InterruptBench) | Collaboration | Supervision, Cooperation |
| [Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents](https://arxiv.org/abs/2603.26233) | [2026/03](https://arxiv.org/abs/2603.26233) | Collaboration | Cooperation |
| [User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction (VARS)](https://arxiv.org/abs/2603.20939) | [2026/03](https://github.com/YurenHao0426/VARS) [![GitHub stars](https://img.shields.io/github/stars/YurenHao0426/VARS?style=social)](https://github.com/YurenHao0426/VARS) | Collaboration | Cooperation |
| [LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks](https://arxiv.org/abs/2604.13072) | [2026/03](https://github.com/Mosi-AI/LiveClawBench) [![GitHub stars](https://img.shields.io/github/stars/Mosi-AI/LiveClawBench?style=social)](https://github.com/Mosi-AI/LiveClawBench) | Collaboration | Delegation |
| [AgentDS: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science](https://arxiv.org/abs/2603.19005) | [2026/03](https://agentds.org/) | Collaboration | Cooperation, Delegation |
| [ViviDoc: Generating Interactive Documents through Human-Agent Collaboration](https://arxiv.org/abs/2603.01912) | [2026/03](https://github.com/MisterBrookT/vividoc) [![GitHub stars](https://img.shields.io/github/stars/MisterBrookT/vividoc?style=social)](https://github.com/MisterBrookT/vividoc) | Collaboration | Cooperation |
| [InfoPO: Information-Driven Policy Optimization for User-Centric Agents](https://arxiv.org/abs/2603.00656) | [2026/02](https://github.com/kfq20/InfoPO) [![GitHub stars](https://img.shields.io/github/stars/kfq20/InfoPO?style=social)](https://github.com/kfq20/InfoPO) | Collaboration | Cooperation |
| [Modeling Distinct Human Interaction in Web Agents (CowCorpus)](https://arxiv.org/abs/2602.17588) | [2026/02](https://arxiv.org/abs/2602.17588) | Collaboration | Supervision, Delegation, Coordination |
| [Overseeing Agents Without Constant Oversight: Challenges and Opportunities](https://arxiv.org/abs/2602.16844) | [2026/02](https://arxiv.org/abs/2602.16844) | Collaboration | Supervision |
| [Learning Personalized Agents from Human Feedback](https://arxiv.org/abs/2602.16173) | [2026/02](https://github.com/facebookresearch/PAHF) [![GitHub stars](https://img.shields.io/github/stars/facebookresearch/PAHF?style=social)](https://github.com/facebookresearch/PAHF) | Collaboration | Cooperation |
| [Value of Information: A Framework for Human-Agent Communication](https://arxiv.org/abs/2601.06407) | [2026/01](https://arxiv.org/abs/2601.06407) | Collaboration | Cooperation |
| [Progressive Ideation using an Agentic AI Framework for Human-AI Co-Creation (MIDAS)](https://arxiv.org/abs/2601.00475) | [2026/01](https://arxiv.org/abs/2601.00475) | Collaboration | Cooperation |
| [From Correctness to Collaboration: Toward a Human-Centered Framework for Evaluating AI Agent Behavior in Software Engineering](https://arxiv.org/abs/2512.23844) | [2025/12](https://arxiv.org/abs/2512.23844) | Collaboration | Supervision, Cooperation |
| [CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding](https://arxiv.org/abs/2512.04111) | [2025/11](https://arxiv.org/abs/2512.04111) | Collaboration | Delegation, Cooperation |
| [Training Proactive and Personalized LLM Agents](https://arxiv.org/abs/2511.02208) | [2025/11](https://github.com/sunnweiwei/PPP-Agent) [![GitHub stars](https://img.shields.io/github/stars/sunnweiwei/PPP-Agent?style=social)](https://github.com/sunnweiwei/PPP-Agent) | Collaboration | Cooperation |
| [Training LLM Agents to Empower Humans](https://arxiv.org/abs/2510.13709) | [2025/10](https://github.com/festusev/codegen_empowerment) [![GitHub stars](https://img.shields.io/github/stars/festusev/codegen_empowerment?style=social)](https://github.com/festusev/codegen_empowerment) | Collaboration | Cooperation |
| [How can we assess human-agent interactions? Case studies in software agent design](https://arxiv.org/abs/2510.09801v2) | [2025/10](https://arxiv.org/abs/2510.09801v2) | Collaboration | Delegation, Supervision |
| [RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback](https://arxiv.org/abs/2510.06186) | [2025/10](https://github.com/ChunyuMiao98/RECODE-H) [![GitHub stars](https://img.shields.io/github/stars/ChunyuMiao98/RECODE-H?style=social)](https://github.com/ChunyuMiao98/RECODE-H) | Collaboration | Supervision, Cooperation |
| [UserRL: Training Proactive User-Centric Agent via Reinforcement Learning](https://arxiv.org/abs/2509.19736) | [2025/09](https://github.com/SalesforceAIResearch/UserRL) [![GitHub stars](https://img.shields.io/github/stars/SalesforceAIResearch/UserRL?style=social)](https://github.com/SalesforceAIResearch/UserRL) | Collaboration | Supervision, Cooperation |
| [MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use](https://arxiv.org/abs/2508.18669) | [2025/08](https://github.com/zzwkk/MUA-RL) [![GitHub stars](https://img.shields.io/github/stars/zzwkk/MUA-RL?style=social)](https://github.com/zzwkk/MUA-RL) | Collaboration | Delegation |
| [Magentic-UI: Towards Human-in-the-loop Agentic Systems](https://www.arxiv.org/abs/2507.22358) | [2025/07](https://github.com/microsoft/magentic-ui) [![GitHub stars](https://img.shields.io/github/stars/microsoft/magentic-ui?style=social)](https://github.com/microsoft/magentic-ui) | Collaboration | Cooperation, Coordination |
| [UserBench: An Interactive Gym Environment for User-Centric Agents](https://arxiv.org/abs/2507.22034) | [2025/07](https://github.com/SalesforceAIResearch/UserBench) [![GitHub stars](https://img.shields.io/github/stars/SalesforceAIResearch/UserBench?style=social)](https://github.com/SalesforceAIResearch/UserBench) | Collaboration | Cooperation |
| [Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance](https://www.arxiv.org/abs/2507.17131) | [2025/07](https://github.com/yf-he/aria) [![GitHub stars](https://img.shields.io/github/stars/yf-he/aria?style=social)](https://github.com/yf-he/aria) | Collaboration | Supervision |
| [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://arxiv.org/abs/2506.07982) | [2025/06](https://github.com/sierra-research/tau2-bench) [![GitHub stars](https://img.shields.io/github/stars/sierra-research/tau2-bench?style=social)](https://github.com/sierra-research/tau2-bench) | Collaboration | Cooperation, Coordination |
| [Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training](https://arxiv.org/abs/2406.00222) | [2025/05](https://github.com/google-research/google-research/tree/master/learning_to_clarify) | Collaboration | Cooperation |
| [Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild](https://arxiv.org/abs/2505.16023) | [2025/05](https://github.com/microsoft/prototypical-hai-collaborations) [![GitHub stars](https://img.shields.io/github/stars/microsoft/prototypical-hai-collaborations?style=social)](https://github.com/microsoft/prototypical-hai-collaborations) | Collaboration | Supervision, Cooperation |
| [XtraGPT: LLMs for Human-AI Collaboration on Controllable Academic Paper Revision](https://arxiv.org/abs/2505.11336) | [2025/05](https://github.com/NuoJohnChen/XtraGPT) [![GitHub stars](https://img.shields.io/github/stars/NuoJohnChen/XtraGPT?style=social)](https://github.com/NuoJohnChen/XtraGPT) | Collaboration | Delegation, Supervision |
| [MineWorld: A Real-Time and Open-Source Interactive World Model on Minecraft](https://arxiv.org/abs/2504.08388) | [2025/04](https://github.com/microsoft/MineWorld) [![GitHub stars](https://img.shields.io/github/stars/microsoft/MineWorld?style=social)](https://github.com/microsoft/MineWorld) | Collaboration | Delegation |
| [Experimental Exploration: Investigating Cooperative Interaction Behavior Between Humans and Large Language Model Agents](https://arxiv.org/abs/2503.07320) | [2025/03](https://arxiv.org/abs/2503.07320) | Coopetition | - |
| [FinArena: A Human-Agent Collaboration Framework for Financial Market Analysis and Forecasting](https://arxiv.org/abs/2503.02692) | [2025/03](https://huggingface.co/datasets/Illogicaler/FinArena-low-cost-dataset) | Collaboration | Delegation |
| [SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks](https://arxiv.org/abs/2503.15478) | [2025/03](https://github.com/facebookresearch/sweet_rl) [![GitHub stars](https://img.shields.io/github/stars/facebookresearch/sweet_rl?style=social)](https://github.com/facebookresearch/sweet_rl) | Collaboration | Delegation |
| [ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments](https://arxiv.org/abs/2502.19852) | [2025/02](https://github.com/stovecat/convcodeworld) [![GitHub stars](https://img.shields.io/github/stars/stovecat/convcodeworld?style=social)](https://github.com/stovecat/convcodeworld) | Collaboration | Supervision, Delegation |
| [Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration](https://arxiv.org/abs/2502.11882) | [2025/02](https://github.com/sjtu-marl/DPT-Agent) [![GitHub stars](https://img.shields.io/github/stars/sjtu-marl/DPT-Agent?style=social)](https://github.com/sjtu-marl/DPT-Agent) | Collaboration | - |
| [CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigation](https://arxiv.org/abs/2501.16609) | [2025/01](https://oaishi.github.io/cowpilot.html) | Collaboration | Supervision, Delegation, Coordination |
| [Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration (Co-Gym)](https://arxiv.org/abs/2412.15701) | [2024/12](https://github.com/SALT-NLP/collaborative-gym) [![GitHub stars](https://img.shields.io/github/stars/SALT-NLP/collaborative-gym?style=social)](https://github.com/SALT-NLP/collaborative-gym) | Collaboration | Supervision, Delegation |
| [Towards Modeling Human-Agentic Collaborative Workflows: A BPMN Extension](https://arxiv.org/abs/2412.05958) | [2024/12](https://github.com/BESSER-PEARL/agentic-bpmn) [![GitHub stars](https://img.shields.io/github/stars/BESSER-PEARL/agentic-bpmn?style=social)](https://github.com/BESSER-PEARL/agentic-bpmn) | Collaboration | Coordination |
| [To Help or Not to Help: LLM-based Attentive Support for Human-Robot Group Interactions](https://ieeexplore.ieee.org/abstract/document/10801517) | [2024/10](https://github.com/HRI-EU/AttentiveSupport) [![GitHub stars](https://img.shields.io/github/stars/HRI-EU/AttentiveSupport?style=social)](https://github.com/HRI-EU/AttentiveSupport) | Collaboration | Coordination |
| [PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-Agent Tasks](https://openreview.net/forum?id=T5QLRRHyL1) | [2024/10](https://github.com/facebookresearch/partnr-planner/tree/main/) [![GitHub stars](https://img.shields.io/github/stars/facebookresearch/partnr-planner?style=social)](https://github.com/facebookresearch/partnr-planner/tree/main/) | Collaboration | Coordination, Cooperation |
| [AssistantX: An  Proactive Assistant in Collaborative Human-Populated Environment](https://arxiv.org/abs/2409.17655) | [2024/09](https://github.com/AssistantX-Agent/AssistantX) [![GitHub stars](https://img.shields.io/github/stars/AssistantX-Agent/AssistantX?style=social)](https://github.com/AssistantX-Agent/AssistantX) | Collaboration | Delegation |
| [Mutual Theory of Mind in Human-AI Collaboration: An Empirical Study with LLM-driven AI Agents in a Real-time Shared Workspace Task](https://arxiv.org/abs/2409.08811) | [2024/09](https://arxiv.org/abs/2409.08811) | Collaboration | Coordination |
| [Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations](https://arxiv.org/abs/2408.15232) | [2024/08](https://github.com/stanford-oval/storm) [![GitHub stars](https://img.shields.io/github/stars/stanford-oval/storm?style=social)](https://github.com/stanford-oval/storm) | Collaboration | Delegation |
| [Human-LLM Collaboration in Generative Design for Customization](https://www.sciencedirect.com/science/article/abs/pii/S0278612525000731) | [2024/07](https://www.sciencedirect.com/science/article/abs/pii/S0278612525000731) | Collaboration | Delegation |
| [DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning](https://arxiv.org/abs/2406.11896) | [2024/06](https://github.com/DigiRL-agent/digirl) [![GitHub stars](https://img.shields.io/github/stars/DigiRL-agent/digirl?style=social)](https://github.com/DigiRL-agent/digirl) | Collaboration | Delegation |
| [Enhancing Human-Robot Collaborative Assembly in Manufacturing Systems Using Large Language Models](https://arxiv.org/abs/2406.01915) | [2024/06](https://arxiv.org/abs/2406.01915) | Collaboration | Delegation |
| [Enhancing the LLM-Based Robot Manipulation Through Human-Robot Collaboration](https://ieeexplore.ieee.org/abstract/document/10561501) | [2024/06](https://ieeexplore.ieee.org/abstract/document/10561501) | Collaboration | Delegation |
| [WebCanvas: Benchmarking Web Agents in Online Environments](https://arxiv.org/pdf/2406.12373) | [2024/06](https://huggingface.co/datasets/iMeanAI/Mind2Web-Live) | Collaboration | Delegation |
| [REVECA: Adaptive Planning and Trajectory-based Validation in Cooperative Language Agents Using Information Relevance and Relative Proximity](https://arxiv.org/abs/2405.16751) | [2024/05](https://arxiv.org/abs/2405.16751) | Collaboration | Delegation |
| [A Human-Computer Collaborative Tool for Training a Single Large Language Model Agent into a Network through Few Examples](https://arxiv.org/abs/2404.15974) | [2024/04](https://arxiv.org/abs/2404.15974) | Collaboration | Delegation, Supervision |
| [AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaboration](https://arxiv.org/abs/2404.11943) | [2024/04](https://github.com/AgentCoord/AgentCoord) [![GitHub stars](https://img.shields.io/github/stars/AgentCoord/AgentCoord?style=social)](https://github.com/AgentCoord/AgentCoord) | Collaboration | Coordination |
| [An LLM-based approach for Enabling Seamless Human-Robot Collaboration in Assembly](https://www.sciencedirect.com/science/article/pii/S000785062400012X) | [2024/04](https://www.sciencedirect.com/science/article/pii/S000785062400012X) | Collaboration | Delegation |
| [Autonomous Evaluation and Refinement of Digital Agents](https://arxiv.org/abs/2404.06474) | [2024/04](https://github.com/Berkeley-NLP/Agent-Eval-Refine) [![GitHub stars](https://img.shields.io/github/stars/Berkeley-NLP/Agent-Eval-Refine?style=social)](https://github.com/Berkeley-NLP/Agent-Eval-Refine) | Collaboration | Delegation |
| [PDFChatAnnotator: A Human-LLM Collaborative Multi-Modal Data Annotation Tool for PDF-Format Catalogs](https://dl.acm.org/doi/abs/10.1145/3640543.3645174) | [2024/04](https://dl.acm.org/doi/abs/10.1145/3640543.3645174) | Collaboration | Delegation |
| [Embodied LLM Agents Learn to Cooperate in Organized Teams](https://arxiv.org/abs/2403.12482) | [2024/03](https://github.com/tobeatraceur/Organized-LLM-Agents) [![GitHub stars](https://img.shields.io/github/stars/tobeatraceur/Organized-LLM-Agents?style=social)](https://github.com/tobeatraceur/Organized-LLM-Agents) | Collaboration | Delegation |
| [Large Language Model-based Human-Agent Collaboration for Complex Task Solving](https://arxiv.org/abs/2402.12914) | [2024/02](https://github.com/XueyangFeng/ReHAC) [![GitHub stars](https://img.shields.io/github/stars/XueyangFeng/ReHAC?style=social)](https://github.com/XueyangFeng/ReHAC) | Collaboration | Delegation |
| [WebLINX: Real-World Website Navigation with Multi-Turn Dialogue](https://arxiv.org/abs/2402.05930) | [2024/02](https://github.com/McGill-NLP/WebLINX) [![GitHub stars](https://img.shields.io/github/stars/McGill-NLP/WebLINX?style=social)](https://github.com/McGill-NLP/WebLINX) | Collaboration | Delegation |
| [A2C: A Modular Multi-stage Collaborative Decision Framework for Human-AI Teams](https://arxiv.org/abs/2401.14432) | [2024/01](https://anonymous.4open.science/r/A2C/README.md) | Collaboration | Coordination |
| [Ask-before-Plan: Proactive Language Agents for Real-World Planning](https://arxiv.org/abs/2406.12639) | [2024/01](https://github.com/magicgh/Ask-before-Plan) [![GitHub stars](https://img.shields.io/github/stars/magicgh/Ask-before-Plan?style=social)](https://github.com/magicgh/Ask-before-Plan) | Collaboration | Coordination |
| [LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination](https://arxiv.org/abs/2312.15224) | [2023/12](https://github.com/HosnLS/Hierarchical-Language-Agent) [![GitHub stars](https://img.shields.io/github/stars/HosnLS/Hierarchical-Language-Agent?style=social)](https://github.com/HosnLS/Hierarchical-Language-Agent) | Collaboration | Supervision, Delegation |
| [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://arxiv.org/abs/2310.11667) | [2023/10](https://arxiv.org/abs/2310.11667) | Collaboration, Competition, Coopetition | Coordination |
| [Drive As You Speak: Enabling Human-Like Interaction With Large Language Models in Autonomous Vehicles](https://arxiv.org/abs/2309.10228) | [2023/09](https://arxiv.org/abs/2309.10228) | Collaboration | Delegation |
| [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://arxiv.org/pdf/2309.10691) | [2023/09](https://xwang.dev/mint-bench/) | Collaboration | Delegation |
| [MindAgent: Emergent Gaming Interaction](https://arxiv.org/abs/2309.09971) | [2023/09](https://github.com/mindagent/mindagent) [![GitHub stars](https://img.shields.io/github/stars/mindagent/mindagent?style=social)](https://github.com/mindagent/mindagent) | Collaboration | Coordination |
| [LLM-Based Human-Robot Collaboration Framework for Manipulation Tasks](https://arxiv.org/abs/2308.14972) | [2023/08](https://arxiv.org/abs/2308.14972) | Collaboration | Supervision, Delegation |
| [MetaGPT: Meta Programming for a Multi-Agent Collaborative Framework](https://arxiv.org/abs/2308.00352) | [2023/08](https://github.com/geekan/MetaGPT) [![GitHub stars](https://img.shields.io/github/stars/geekan/MetaGPT?style=social)](https://github.com/geekan/MetaGPT) | Collaboration | Coordination |
| [Building Cooperative Embodied Agents Modularly with Large Language Models](https://arxiv.org/abs/2307.02485) | [2023/07](https://arxiv.org/abs/2307.02485) | Collaboration | Cooperation |
| [Embodied Task Planning with Large Language Models](https://arxiv.org/abs/2307.01848) | [2023/07](https://github.com/Gary3410/TaPA) [![GitHub stars](https://img.shields.io/github/stars/Gary3410/TaPA?style=social)](https://github.com/Gary3410/TaPA) | Collaboration | Delegation |
| [Improved Trust in Human-Robot Collaboration With ChatGPT](https://ieeexplore.ieee.org/abstract/document/10141597) | [2023/06](https://ieeexplore.ieee.org/abstract/document/10141597) | Collaboration | Delegation |
| [Investigating Agency of LLMs in Human-AI Collaboration Tasks](https://arxiv.org/abs/2305.12815) | [2023/05](https://arxiv.org/abs/2305.12815) | Collaboration | Cooperation, Delegation |
| [Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents through Help Feedback](https://arxiv.org/abs/2304.10750) | [2023/04](https://arxiv.org/abs/2304.10750) | Collaboration | Delegation |
| [PaLM-E: An Embodied Multimodal Language Model](https://openreview.net/forum?id=VTpHpqM3Cf&utm_campaign=The%20Batch&utm_source=hs_email&utm_medium=email&utm_content=284568789&_hsenc=p2ANqtz-9lsSL4nXMrOGBQqGoqktY5Yno_r9-nTOARZinDcgihFNqcOFEQb_MVtHKdpgI2AC3N8SrNW5PxcD0uxl4WeKcPJgUOgw) | [2023/03](https://palm-e.github.io) | Collaboration | Delegation |
| [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://dl.acm.org/doi/abs/10.1145/3491102.3517582) | [2021/10](https://dl.acm.org/doi/abs/10.1145/3491102.3517582) | Collaboration | Delegation |

---

| Title | Date & Code | Orchestration Strategy | Orchestration Synchronization |
| --- | :---: | :---: | :---: |
| [Just A Rather Very Intelligent Spoken Agent (JarvisBench)](https://arxiv.org/abs/2607.16610) | [2026/07](https://cchen1436.github.io/jarvis) | Simultaneous | Asynchronous |
| [LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability](https://arxiv.org/abs/2607.06157) | [2026/07](https://github.com/wcx21/deliberative-collaboration-agents) [![GitHub stars](https://img.shields.io/github/stars/wcx21/deliberative-collaboration-agents?style=social)](https://github.com/wcx21/deliberative-collaboration-agents) | One-by-One | Synchronous |
| [HAS-Bench: Evaluating LLM-Based Human-Agent Systems under Configurable Human Participation](https://arxiv.org/abs/2607.04329) | [2026/07](https://arxiv.org/abs/2607.04329) | One-by-One | Synchronous |
| [PerspectiveGap: A Benchmark for Multi-Agent Orchestration Prompting](https://arxiv.org/abs/2606.08878) | [2026/06](https://github.com/WhymustIhaveaname/PerspectiveGap) [![GitHub stars](https://img.shields.io/github/stars/WhymustIhaveaname/PerspectiveGap?style=social)](https://github.com/WhymustIhaveaname/PerspectiveGap) | Simultaneous | Asynchronous |
| [Uncertainty Decomposition for Clarification Seeking in LLM Agents](https://arxiv.org/abs/2606.19559) | [2026/06](https://arxiv.org/abs/2606.19559) | One-by-One | Synchronous |
| [Learning User Simulators with Turing Rewards](https://arxiv.org/abs/2606.19336) | [2026/06](https://arxiv.org/abs/2606.19336) | One-by-One | Synchronous |
| [Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents (TRACE)](https://arxiv.org/abs/2606.13174) | [2026/06](https://github.com/YujunZhou/tellonce) [![GitHub stars](https://img.shields.io/github/stars/YujunZhou/tellonce?style=social)](https://github.com/YujunZhou/tellonce) | One-by-One | Synchronous |
| [Re-Centering Humans in LLM Personalization](https://arxiv.org/abs/2606.06614) | [2026/06](https://arxiv.org/abs/2606.06614) | One-by-One | Asynchronous |
| [CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement](https://arxiv.org/abs/2606.05793) | [2026/06](https://arxiv.org/abs/2606.05793) | Simultaneous | Synchronous |
| [Human Oversight of Agentic Systems in Practice: Examining the Oversight Work, Challenges, and Heuristics of Developers Using Software Agents](https://arxiv.org/abs/2606.05391) | [2026/06](https://arxiv.org/abs/2606.05391) | One-by-One | Asynchronous |
| [Uncertainty-Aware Clarification in LLM Agents with Information Gain](https://arxiv.org/abs/2606.03135) | [2026/06](https://arxiv.org/abs/2606.03135) | One-by-One | Synchronous |
| [Not All Uncertainty Is Equal: How Uncertainty Granularity Shapes Human Verification in LLM-Assisted Decision Making](https://arxiv.org/abs/2605.28571) | [2026/05](https://arxiv.org/abs/2605.28571) | One-by-One | Synchronous |
| [VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions](https://arxiv.org/abs/2605.27141) | [2026/05](https://github.com/meituan-longcat/VitaBench-2.0) [![GitHub stars](https://img.shields.io/github/stars/meituan-longcat/VitaBench-2.0?style=social)](https://github.com/meituan-longcat/VitaBench-2.0) | One-by-One | Synchronous |
| [Reinforcing Human Behavior Simulation via Verbal Feedback (DITTO & SOUL)](https://arxiv.org/abs/2605.20506) | [2026/05](https://arxiv.org/abs/2605.20506) | One-by-One | Synchronous |
| [ECHO: Explainable Co-editing with Human-in-the-loop Operations for Presentation Refinement](https://arxiv.org/abs/2606.09851) | [2026/05](https://arxiv.org/abs/2606.09851) | One-by-One | Synchronous |
| [AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators](https://arxiv.org/abs/2605.08647) | [2026/05](https://arxiv.org/abs/2605.08647) | One-by-One | Synchronous |
| [SalesSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators](https://arxiv.org/abs/2605.08334) | [2026/05](https://arxiv.org/abs/2605.08334) | One-by-One | Synchronous |
| [A Decoupled Human-in-the-Loop System for Controlled Autonomy in Agentic Workflows](https://arxiv.org/abs/2604.23049) | [2026/04](https://arxiv.org/abs/2604.23049) | One-by-One | Asynchronous |
| [CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks](https://arxiv.org/abs/2606.09833) | [2026/04](https://arxiv.org/abs/2606.09833) | One-by-One | Synchronous |
| [When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation (InterruptBench)](https://arxiv.org/abs/2604.00892) | [2026/04](https://github.com/HenryPengZou/InterruptBench) [![GitHub stars](https://img.shields.io/github/stars/HenryPengZou/InterruptBench?style=social)](https://github.com/HenryPengZou/InterruptBench) | One-by-One | Synchronous |
| [Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents](https://arxiv.org/abs/2603.26233) | [2026/03](https://arxiv.org/abs/2603.26233) | One-by-One | Synchronous |
| [User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction (VARS)](https://arxiv.org/abs/2603.20939) | [2026/03](https://github.com/YurenHao0426/VARS) [![GitHub stars](https://img.shields.io/github/stars/YurenHao0426/VARS?style=social)](https://github.com/YurenHao0426/VARS) | One-by-One | Synchronous |
| [LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks](https://arxiv.org/abs/2604.13072) | [2026/03](https://github.com/Mosi-AI/LiveClawBench) [![GitHub stars](https://img.shields.io/github/stars/Mosi-AI/LiveClawBench?style=social)](https://github.com/Mosi-AI/LiveClawBench) | One-by-One | Asynchronous |
| [AgentDS: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science](https://arxiv.org/abs/2603.19005) | [2026/03](https://agentds.org/) | One-by-One | Asynchronous |
| [ViviDoc: Generating Interactive Documents through Human-Agent Collaboration](https://arxiv.org/abs/2603.01912) | [2026/03](https://github.com/MisterBrookT/vividoc) [![GitHub stars](https://img.shields.io/github/stars/MisterBrookT/vividoc?style=social)](https://github.com/MisterBrookT/vividoc) | One-by-One | Synchronous |
| [InfoPO: Information-Driven Policy Optimization for User-Centric Agents](https://arxiv.org/abs/2603.00656) | [2026/02](https://github.com/kfq20/InfoPO) [![GitHub stars](https://img.shields.io/github/stars/kfq20/InfoPO?style=social)](https://github.com/kfq20/InfoPO) | One-by-One | Synchronous |
| [Modeling Distinct Human Interaction in Web Agents (CowCorpus)](https://arxiv.org/abs/2602.17588) | [2026/02](https://arxiv.org/abs/2602.17588) | Simultaneous | Synchronous |
| [Overseeing Agents Without Constant Oversight: Challenges and Opportunities](https://arxiv.org/abs/2602.16844) | [2026/02](https://arxiv.org/abs/2602.16844) | One-by-One | Asynchronous |
| [Learning Personalized Agents from Human Feedback](https://arxiv.org/abs/2602.16173) | [2026/02](https://github.com/facebookresearch/PAHF) [![GitHub stars](https://img.shields.io/github/stars/facebookresearch/PAHF?style=social)](https://github.com/facebookresearch/PAHF) | One-by-One | Synchronous |
| [Value of Information: A Framework for Human-Agent Communication](https://arxiv.org/abs/2601.06407) | [2026/01](https://arxiv.org/abs/2601.06407) | One-by-One | Synchronous |
| [Progressive Ideation using an Agentic AI Framework for Human-AI Co-Creation (MIDAS)](https://arxiv.org/abs/2601.00475) | [2026/01](https://arxiv.org/abs/2601.00475) | One-by-One | Synchronous |
| [From Correctness to Collaboration: Toward a Human-Centered Framework for Evaluating AI Agent Behavior in Software Engineering](https://arxiv.org/abs/2512.23844) | [2025/12](https://arxiv.org/abs/2512.23844) | One-by-One | Synchronous |
| [CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding](https://arxiv.org/abs/2512.04111) | [2025/11](https://arxiv.org/abs/2512.04111) | Simultaneous | Synchronous |
| [Training Proactive and Personalized LLM Agents](https://arxiv.org/abs/2511.02208) | [2025/11](https://github.com/sunnweiwei/PPP-Agent) [![GitHub stars](https://img.shields.io/github/stars/sunnweiwei/PPP-Agent?style=social)](https://github.com/sunnweiwei/PPP-Agent) | One-by-One | Synchronous |
| [Training LLM Agents to Empower Humans](https://arxiv.org/abs/2510.13709) | [2025/10](https://github.com/festusev/codegen_empowerment) [![GitHub stars](https://img.shields.io/github/stars/festusev/codegen_empowerment?style=social)](https://github.com/festusev/codegen_empowerment) | One-by-One | Synchronous |
| [How can we assess human-agent interactions? Case studies in software agent design](https://arxiv.org/abs/2510.09801v2) | [2025/10](https://arxiv.org/abs/2510.09801v2) | One-by-One | Synchronous |
| [RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback](https://arxiv.org/abs/2510.06186) | [2025/10](https://github.com/ChunyuMiao98/RECODE-H) [![GitHub stars](https://img.shields.io/github/stars/ChunyuMiao98/RECODE-H?style=social)](https://github.com/ChunyuMiao98/RECODE-H) | One-by-One | Synchronous |
| [UserRL: Training Proactive User-Centric Agent via Reinforcement Learning](https://arxiv.org/abs/2509.19736) | [2025/09](https://github.com/SalesforceAIResearch/UserRL) [![GitHub stars](https://img.shields.io/github/stars/SalesforceAIResearch/UserRL?style=social)](https://github.com/SalesforceAIResearch/UserRL) | One-by-One | Synchronous |
| [MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use](https://arxiv.org/abs/2508.18669) | [2025/08](https://github.com/zzwkk/MUA-RL) [![GitHub stars](https://img.shields.io/github/stars/zzwkk/MUA-RL?style=social)](https://github.com/zzwkk/MUA-RL) | One-by-One | Synchronous |
| [Magentic-UI: Towards Human-in-the-loop Agentic Systems](https://www.arxiv.org/abs/2507.22358) | [2025/07](https://github.com/microsoft/magentic-ui) [![GitHub stars](https://img.shields.io/github/stars/microsoft/magentic-ui?style=social)](https://github.com/microsoft/magentic-ui) | Simultaneous | Synchronous |
| [UserBench: An Interactive Gym Environment for User-Centric Agents](https://arxiv.org/abs/2507.22034) | [2025/07](https://github.com/SalesforceAIResearch/UserBench) [![GitHub stars](https://img.shields.io/github/stars/SalesforceAIResearch/UserBench?style=social)](https://github.com/SalesforceAIResearch/UserBench) | One-by-One | Synchronous |
| [Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance](https://www.arxiv.org/abs/2507.17131) | [2025/07](https://github.com/yf-he/aria) [![GitHub stars](https://img.shields.io/github/stars/yf-he/aria?style=social)](https://github.com/yf-he/aria) | One-by-One | Synchronous |
| [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://arxiv.org/abs/2506.07982) | [2025/06](https://github.com/sierra-research/tau2-bench) [![GitHub stars](https://img.shields.io/github/stars/sierra-research/tau2-bench?style=social)](https://github.com/sierra-research/tau2-bench) | One-by-One | Synchronous |
| [Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training](https://arxiv.org/abs/2406.00222) | [2025/05](https://github.com/google-research/google-research/tree/master/learning_to_clarify) | One-by-One | Synchronous |
| [Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild](https://arxiv.org/abs/2505.16023) | [2025/05](https://github.com/microsoft/prototypical-hai-collaborations) [![GitHub stars](https://img.shields.io/github/stars/microsoft/prototypical-hai-collaborations?style=social)](https://github.com/microsoft/prototypical-hai-collaborations) | One-by-One | Synchronous |
| [XtraGPT: LLMs for Human-AI Collaboration on Controllable Academic Paper Revision](https://arxiv.org/abs/2505.11336) | [2025/05](https://github.com/NuoJohnChen/XtraGPT) [![GitHub stars](https://img.shields.io/github/stars/NuoJohnChen/XtraGPT?style=social)](https://github.com/NuoJohnChen/XtraGPT) | One-by-One | Synchronous |
| [MineWorld: A Real-Time and Open-Source Interactive World Model on Minecraft](https://arxiv.org/abs/2504.08388) | [2025/04](https://github.com/microsoft/MineWorld) [![GitHub stars](https://img.shields.io/github/stars/microsoft/MineWorld?style=social)](https://github.com/microsoft/MineWorld) | One-by-One | Synchronous |
| [Experimental Exploration: Investigating Cooperative Interaction Behavior Between Humans and Large Language Model Agents](https://arxiv.org/abs/2503.07320) | [2025/03](https://arxiv.org/abs/2503.07320) | One-by-One | Synchronous |
| [FinArena: A Human-Agent Collaboration Framework for Financial Market Analysis and Forecasting](https://arxiv.org/abs/2503.02692) | [2025/03](https://huggingface.co/datasets/Illogicaler/FinArena-low-cost-dataset) | One-by-One | Synchronous |
| [SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks](https://arxiv.org/abs/2503.15478) | [2025/03](https://github.com/facebookresearch/sweet_rl) [![GitHub stars](https://img.shields.io/github/stars/facebookresearch/sweet_rl?style=social)](https://github.com/facebookresearch/sweet_rl) | One-by-One | Synchronous |
| [ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments](https://arxiv.org/abs/2502.19852) | [2025/02](https://github.com/stovecat/convcodeworld) [![GitHub stars](https://img.shields.io/github/stars/stovecat/convcodeworld?style=social)](https://github.com/stovecat/convcodeworld) | One-by-One | Asynchronous |
| [Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration](https://arxiv.org/abs/2502.11882) | [2025/02](https://github.com/sjtu-marl/DPT-Agent) [![GitHub stars](https://img.shields.io/github/stars/sjtu-marl/DPT-Agent?style=social)](https://github.com/sjtu-marl/DPT-Agent) | Simultaneous | Asynchronous |
| [CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigation](https://arxiv.org/abs/2501.16609) | [2025/01](https://oaishi.github.io/cowpilot.html) | One-by-One | Synchronous |
| [Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration (Co-Gym)](https://arxiv.org/abs/2412.15701) | [2024/12](https://github.com/SALT-NLP/collaborative-gym) [![GitHub stars](https://img.shields.io/github/stars/SALT-NLP/collaborative-gym?style=social)](https://github.com/SALT-NLP/collaborative-gym) | One-by-One | Asynchronous |
| [Towards Modeling Human-Agentic Collaborative Workflows: A BPMN Extension](https://arxiv.org/abs/2412.05958) | [2024/12](https://github.com/BESSER-PEARL/agentic-bpmn) [![GitHub stars](https://img.shields.io/github/stars/BESSER-PEARL/agentic-bpmn?style=social)](https://github.com/BESSER-PEARL/agentic-bpmn) | One-by-One | Asynchronous |
| [To Help or Not to Help: LLM-based Attentive Support for Human-Robot Group Interactions](https://ieeexplore.ieee.org/abstract/document/10801517) | [2024/10](https://github.com/HRI-EU/AttentiveSupport) [![GitHub stars](https://img.shields.io/github/stars/HRI-EU/AttentiveSupport?style=social)](https://github.com/HRI-EU/AttentiveSupport) | One-by-One | Synchronous |
| [PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-Agent Tasks](https://openreview.net/forum?id=T5QLRRHyL1) | [2024/10](https://github.com/facebookresearch/partnr-planner/tree/main/) [![GitHub stars](https://img.shields.io/github/stars/facebookresearch/partnr-planner?style=social)](https://github.com/facebookresearch/partnr-planner/tree/main/) | One-by-One | Asynchronous |
| [AssistantX: An LLM-Powered Proactive Assistant in Collaborative Human-Populated Environment](https://arxiv.org/abs/2409.17655) | [2024/09](https://github.com/AssistantX-Agent/AssistantX) [![GitHub stars](https://img.shields.io/github/stars/AssistantX-Agent/AssistantX?style=social)](https://github.com/AssistantX-Agent/AssistantX) | One-by-One | Asynchronous |
| [Mutual Theory of Mind in Human-AI Collaboration: An Empirical Study with LLM-driven AI Agents in a Real-time Shared Workspace Task](https://arxiv.org/abs/2409.08811) | [2024/09](https://arxiv.org/abs/2409.08811) | Simultaneous | Synchronous |
| [Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations](https://arxiv.org/abs/2408.15232) | [2024/08](https://github.com/stanford-oval/storm) [![GitHub stars](https://img.shields.io/github/stars/stanford-oval/storm?style=social)](https://github.com/stanford-oval/storm) | One-by-One | Synchronous |
| [Human-LLM Collaboration in Generative Design for Customization](https://www.sciencedirect.com/science/article/abs/pii/S0278612525000731) | [2024/07](https://www.sciencedirect.com/science/article/abs/pii/S0278612525000731) | One-by-One | Synchronous |
| [DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning](https://arxiv.org/abs/2406.11896) | [2024/06](https://github.com/DigiRL-agent/digirl) [![GitHub stars](https://img.shields.io/github/stars/DigiRL-agent/digirl?style=social)](https://github.com/DigiRL-agent/digirl) | One-by-One | Asynchronous |
| [Enhancing Human-Robot Collaborative Assembly in Manufacturing Systems Using Large Language Models](https://arxiv.org/abs/2406.01915) | [2024/06](https://arxiv.org/abs/2406.01915) | One-by-One | Synchronous |
| [Enhancing the LLM-Based Robot Manipulation Through Human-Robot Collaboration](https://ieeexplore.ieee.org/abstract/document/10561501) | [2024/06](https://ieeexplore.ieee.org/abstract/document/10561501) | One-by-One | Synchronous |
| [WebCanvas: Benchmarking Web Agents in Online Environments](https://arxiv.org/pdf/2406.12373) | [2024/06](https://huggingface.co/datasets/iMeanAI/Mind2Web-Live) | One-by-One | Synchronous |
| [REVECA: Adaptive Planning and Trajectory-based Validation in Cooperative Language Agents Using Information Relevance and Relative Proximity](https://arxiv.org/abs/2405.16751) | [2024/05](https://arxiv.org/abs/2405.16751) | One-by-One | Asynchronous |
| [A Human-Computer Collaborative Tool for Training a Single Large Language Model Agent into a Network through Few Examples](https://arxiv.org/abs/2404.15974) | [2024/04](https://arxiv.org/abs/2404.15974) | One-by-One | Synchronous |
| [AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaboration](https://arxiv.org/abs/2404.11943) | [2024/04](https://github.com/AgentCoord/AgentCoord) [![GitHub stars](https://img.shields.io/github/stars/AgentCoord/AgentCoord?style=social)](https://github.com/AgentCoord/AgentCoord) | One-by-One | Synchronous |
| [An LLM-based approach for Enabling Seamless Human-Robot Collaboration in Assembly](https://www.sciencedirect.com/science/article/pii/S000785062400012X) | [2024/04](https://www.sciencedirect.com/science/article/pii/S000785062400012X) | One-by-One | Synchronous |
| [Autonomous Evaluation and Refinement of Digital Agents](https://arxiv.org/abs/2404.06474) | [2024/04](https://github.com/Berkeley-NLP/Agent-Eval-Refine) [![GitHub stars](https://img.shields.io/github/stars/Berkeley-NLP/Agent-Eval-Refine?style=social)](https://github.com/Berkeley-NLP/Agent-Eval-Refine) | One-by-One | Asynchronous |
| [PDFChatAnnotator: A Human-LLM Collaborative Multi-Modal Data Annotation Tool for PDF-Format Catalogs](https://dl.acm.org/doi/abs/10.1145/3640543.3645174) | [2024/04](https://dl.acm.org/doi/abs/10.1145/3640543.3645174) | One-by-One | Synchronous |
| [Embodied LLM Agents Learn to Cooperate in Organized Teams](https://arxiv.org/abs/2403.12482) | [2024/03](https://github.com/tobeatraceur/Organized-LLM-Agents) [![GitHub stars](https://img.shields.io/github/stars/tobeatraceur/Organized-LLM-Agents?style=social)](https://github.com/tobeatraceur/Organized-LLM-Agents) | One-by-One | Synchronous |
| [Large Language Model-based Human-Agent Collaboration for Complex Task Solving](https://arxiv.org/abs/2402.12914) | [2024/02](https://github.com/XueyangFeng/ReHAC) [![GitHub stars](https://img.shields.io/github/stars/XueyangFeng/ReHAC?style=social)](https://github.com/XueyangFeng/ReHAC) | One-by-One | Synchronous |
| [WebLINX: Real-World Website Navigation with Multi-Turn Dialogue](https://arxiv.org/abs/2402.05930) | [2024/02](https://github.com/McGill-NLP/WebLINX) [![GitHub stars](https://img.shields.io/github/stars/McGill-NLP/WebLINX?style=social)](https://github.com/McGill-NLP/WebLINX) | One-by-One | Synchronous |
| [A2C: A Modular Multi-stage Collaborative Decision Framework for Human-AI Teams](https://arxiv.org/abs/2401.14432) | [2024/01](https://anonymous.4open.science/r/A2C/README.md) | One-by-One | Asynchronous |
| [Ask-before-Plan: Proactive Language Agents for Real-World Planning](https://arxiv.org/abs/2406.12639) | [2024/01](https://github.com/magicgh/Ask-before-Plan) [![GitHub stars](https://img.shields.io/github/stars/magicgh/Ask-before-Plan?style=social)](https://github.com/magicgh/Ask-before-Plan) | One-by-One | Synchronous |
| [LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination](https://arxiv.org/abs/2312.15224) | [2023/12](https://github.com/HosnLS/Hierarchical-Language-Agent) [![GitHub stars](https://img.shields.io/github/stars/HosnLS/Hierarchical-Language-Agent?style=social)](https://github.com/HosnLS/Hierarchical-Language-Agent) | Simultaneous | Synchronous |
| [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://arxiv.org/abs/2310.11667) | [2023/10](https://arxiv.org/abs/2310.11667) | One-by-One | Synchronous |
| [Drive As You Speak: Enabling Human-Like Interaction With Large Language Models in Autonomous Vehicles](https://arxiv.org/abs/2309.10228) | [2023/09](https://arxiv.org/abs/2309.10228) | One-by-One | Synchronous |
| [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://arxiv.org/pdf/2309.10691) | [2023/09](https://xwang.dev/mint-bench/) | One-by-One | Synchronous |
| [MindAgent: Emergent Gaming Interaction](https://arxiv.org/abs/2309.09971) | [2023/09](https://github.com/mindagent/mindagent) [![GitHub stars](https://img.shields.io/github/stars/mindagent/mindagent?style=social)](https://github.com/mindagent/mindagent) | One-by-One | Synchronous |
| [LLM-Based Human-Robot Collaboration Framework for Manipulation Tasks](https://arxiv.org/abs/2308.14972) | [2023/08](https://arxiv.org/abs/2308.14972) | One-by-One | Synchronous |
| [MetaGPT: Meta Programming for a Multi-Agent Collaborative Framework](https://arxiv.org/abs/2308.00352) | [2023/08](https://github.com/geekan/MetaGPT) [![GitHub stars](https://img.shields.io/github/stars/geekan/MetaGPT?style=social)](https://github.com/geekan/MetaGPT) | One-by-One | Asynchronous |
| [Building Cooperative Embodied Agents Modularly with Large Language Models](https://arxiv.org/abs/2307.02485) | [2023/07](https://arxiv.org/abs/2307.02485) | Simultaneous | Synchronous |
| [Embodied Task Planning with Large Language Models](https://arxiv.org/abs/2307.01848) | [2023/07](https://github.com/Gary3410/TaPA) [![GitHub stars](https://img.shields.io/github/stars/Gary3410/TaPA?style=social)](https://github.com/Gary3410/TaPA) | One-by-One | Asynchronous |
| [Improved Trust in Human-Robot Collaboration With ChatGPT](https://ieeexplore.ieee.org/abstract/document/10141597) | [2023/06](https://ieeexplore.ieee.org/abstract/document/10141597) | One-by-One | Synchronous |
| [Investigating Agency of LLMs in Human-AI Collaboration Tasks](https://arxiv.org/abs/2305.12815) | [2023/05](https://arxiv.org/abs/2305.12815) | One-by-One | Synchronous |
| [Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents through Help Feedback](https://arxiv.org/abs/2304.10750) | [2023/04](https://arxiv.org/abs/2304.10750) | One-by-One | Synchronous |
| [PaLM-E: An Embodied Multimodal Language Model](https://openreview.net/forum?id=VTpHpqM3Cf&utm_campaign=The%20Batch&utm_source=hs_email&utm_medium=email&utm_content=284568789&_hsenc=p2ANqtz-9lsSL4nXMrOGBQqGoqktY5Yno_r9-nTOARZinDcgihFNqcOFEQb_MVtHKdpgI2AC3N8SrNW5PxcD0uxl4WeKcPJgUOgw) | [2023/03](https://palm-e.github.io) | One-by-One | Synchronous |
| [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://dl.acm.org/doi/abs/10.1145/3491102.3517582) | [2021/10](https://dl.acm.org/doi/abs/10.1145/3491102.3517582) | One-by-One | Synchronous |

---

| Title | Date & Code | Communication Structure | Communication Mode |
| --- | :---: | :---: | :---: |
| [Just A Rather Very Intelligent Spoken Agent (JarvisBench)](https://arxiv.org/abs/2607.16610) | [2026/07](https://cchen1436.github.io/jarvis) | Hierarchical | Conversation, Observation |
| [LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability](https://arxiv.org/abs/2607.06157) | [2026/07](https://github.com/wcx21/deliberative-collaboration-agents) [![GitHub stars](https://img.shields.io/github/stars/wcx21/deliberative-collaboration-agents?style=social)](https://github.com/wcx21/deliberative-collaboration-agents) | Decentralized | Conversation |
| [HAS-Bench: Evaluating LLM-Based Human-Agent Systems under Configurable Human Participation](https://arxiv.org/abs/2607.04329) | [2026/07](https://arxiv.org/abs/2607.04329) | Hierarchical, Centralized | Conversation, Observation |
| [Uncertainty Decomposition for Clarification Seeking in LLM Agents](https://arxiv.org/abs/2606.19559) | [2026/06](https://arxiv.org/abs/2606.19559) | Centralized | Conversation |
| [Learning User Simulators with Turing Rewards](https://arxiv.org/abs/2606.19336) | [2026/06](https://arxiv.org/abs/2606.19336) | Decentralized | Conversation |
| [Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents (TRACE)](https://arxiv.org/abs/2606.13174) | [2026/06](https://github.com/YujunZhou/tellonce) [![GitHub stars](https://img.shields.io/github/stars/YujunZhou/tellonce?style=social)](https://github.com/YujunZhou/tellonce) | Hierarchical | Conversation |
| [Re-Centering Humans in LLM Personalization](https://arxiv.org/abs/2606.06614) | [2026/06](https://arxiv.org/abs/2606.06614) | Centralized | Conversation |
| [CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement](https://arxiv.org/abs/2606.05793) | [2026/06](https://arxiv.org/abs/2606.05793) | Decentralized | Conversation, Observation |
| [Human Oversight of Agentic Systems in Practice: Examining the Oversight Work, Challenges, and Heuristics of Developers Using Software Agents](https://arxiv.org/abs/2606.05391) | [2026/06](https://arxiv.org/abs/2606.05391) | Hierarchical | Observation, Conversation |
| [Uncertainty-Aware Clarification in LLM Agents with Information Gain](https://arxiv.org/abs/2606.03135) | [2026/06](https://arxiv.org/abs/2606.03135) | Centralized | Conversation |
| [Not All Uncertainty Is Equal: How Uncertainty Granularity Shapes Human Verification in LLM-Assisted Decision Making](https://arxiv.org/abs/2605.28571) | [2026/05](https://arxiv.org/abs/2605.28571) | Centralized | Conversation |
| [VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions](https://arxiv.org/abs/2605.27141) | [2026/05](https://github.com/meituan-longcat/VitaBench-2.0) [![GitHub stars](https://img.shields.io/github/stars/meituan-longcat/VitaBench-2.0?style=social)](https://github.com/meituan-longcat/VitaBench-2.0) | Centralized | Conversation |
| [Reinforcing Human Behavior Simulation via Verbal Feedback (DITTO & SOUL)](https://arxiv.org/abs/2605.20506) | [2026/05](https://arxiv.org/abs/2605.20506) | Decentralized | Conversation |
| [ECHO: Explainable Co-editing with Human-in-the-loop Operations for Presentation Refinement](https://arxiv.org/abs/2606.09851) | [2026/05](https://arxiv.org/abs/2606.09851) | Hierarchical | Conversation, Observation |
| [AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators](https://arxiv.org/abs/2605.08647) | [2026/05](https://arxiv.org/abs/2605.08647) | Decentralized | Message Pool |
| [SalesSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators](https://arxiv.org/abs/2605.08334) | [2026/05](https://arxiv.org/abs/2605.08334) | Centralized | Conversation, Observation |
| [A Decoupled Human-in-the-Loop System for Controlled Autonomy in Agentic Workflows](https://arxiv.org/abs/2604.23049) | [2026/04](https://arxiv.org/abs/2604.23049) | Hierarchical | Conversation |
| [CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks](https://arxiv.org/abs/2606.09833) | [2026/04](https://arxiv.org/abs/2606.09833) | Centralized | Conversation |
| [When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation (InterruptBench)](https://arxiv.org/abs/2604.00892) | [2026/04](https://github.com/HenryPengZou/InterruptBench) [![GitHub stars](https://img.shields.io/github/stars/HenryPengZou/InterruptBench?style=social)](https://github.com/HenryPengZou/InterruptBench) | Centralized | Conversation |
| [Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents](https://arxiv.org/abs/2603.26233) | [2026/03](https://arxiv.org/abs/2603.26233) | Hierarchical | Conversation |
| [User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction (VARS)](https://arxiv.org/abs/2603.20939) | [2026/03](https://github.com/YurenHao0426/VARS) [![GitHub stars](https://img.shields.io/github/stars/YurenHao0426/VARS?style=social)](https://github.com/YurenHao0426/VARS) | Centralized | Conversation |
| [LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks](https://arxiv.org/abs/2604.13072) | [2026/03](https://github.com/Mosi-AI/LiveClawBench) [![GitHub stars](https://img.shields.io/github/stars/Mosi-AI/LiveClawBench?style=social)](https://github.com/Mosi-AI/LiveClawBench) | Centralized | Observation, Conversation |
| [AgentDS: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science](https://arxiv.org/abs/2603.19005) | [2026/03](https://agentds.org/) | Centralized | Conversation |
| [ViviDoc: Generating Interactive Documents through Human-Agent Collaboration](https://arxiv.org/abs/2603.01912) | [2026/03](https://github.com/MisterBrookT/vividoc) [![GitHub stars](https://img.shields.io/github/stars/MisterBrookT/vividoc?style=social)](https://github.com/MisterBrookT/vividoc) | Hierarchical | Conversation |
| [InfoPO: Information-Driven Policy Optimization for User-Centric Agents](https://arxiv.org/abs/2603.00656) | [2026/02](https://github.com/kfq20/InfoPO) [![GitHub stars](https://img.shields.io/github/stars/kfq20/InfoPO?style=social)](https://github.com/kfq20/InfoPO) | Centralized | Conversation |
| [Modeling Distinct Human Interaction in Web Agents (CowCorpus)](https://arxiv.org/abs/2602.17588) | [2026/02](https://arxiv.org/abs/2602.17588) | Centralized | Observation, Conversation |
| [Overseeing Agents Without Constant Oversight: Challenges and Opportunities](https://arxiv.org/abs/2602.16844) | [2026/02](https://arxiv.org/abs/2602.16844) | Hierarchical | Observation |
| [Learning Personalized Agents from Human Feedback](https://arxiv.org/abs/2602.16173) | [2026/02](https://github.com/facebookresearch/PAHF) [![GitHub stars](https://img.shields.io/github/stars/facebookresearch/PAHF?style=social)](https://github.com/facebookresearch/PAHF) | Centralized | Conversation |
| [Value of Information: A Framework for Human-Agent Communication](https://arxiv.org/abs/2601.06407) | [2026/01](https://arxiv.org/abs/2601.06407) | Centralized | Conversation |
| [Progressive Ideation using an Agentic AI Framework for Human-AI Co-Creation (MIDAS)](https://arxiv.org/abs/2601.00475) | [2026/01](https://arxiv.org/abs/2601.00475) | Decentralized | Conversation |
| [From Correctness to Collaboration: Toward a Human-Centered Framework for Evaluating AI Agent Behavior in Software Engineering](https://arxiv.org/abs/2512.23844) | [2025/12](https://arxiv.org/abs/2512.23844) | Hierarchical | Conversation |
| [CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding](https://arxiv.org/abs/2512.04111) | [2025/11](https://arxiv.org/abs/2512.04111) | Centralized | Conversation, Observation |
| [Training Proactive and Personalized LLM Agents](https://arxiv.org/abs/2511.02208) | [2025/11](https://github.com/sunnweiwei/PPP-Agent) [![GitHub stars](https://img.shields.io/github/stars/sunnweiwei/PPP-Agent?style=social)](https://github.com/sunnweiwei/PPP-Agent) | Decentralized | Conversation |
| [Training LLM Agents to Empower Humans](https://arxiv.org/abs/2510.13709) | [2025/10](https://github.com/festusev/codegen_empowerment) [![GitHub stars](https://img.shields.io/github/stars/festusev/codegen_empowerment?style=social)](https://github.com/festusev/codegen_empowerment) | Hierarchical | Conversation, Observation |
| [How can we assess human-agent interactions? Case studies in software agent design](https://arxiv.org/abs/2510.09801v2) | [2025/10](https://arxiv.org/abs/2510.09801v2) | Hierarchical | Conversation |
| [RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback](https://arxiv.org/abs/2510.06186) | [2025/10](https://github.com/ChunyuMiao98/RECODE-H) [![GitHub stars](https://img.shields.io/github/stars/ChunyuMiao98/RECODE-H?style=social)](https://github.com/ChunyuMiao98/RECODE-H) | Hierarchical | Conversation |
| [UserRL: Training Proactive User-Centric Agent via Reinforcement Learning](https://arxiv.org/abs/2509.19736) | [2025/09](https://github.com/SalesforceAIResearch/UserRL) [![GitHub stars](https://img.shields.io/github/stars/SalesforceAIResearch/UserRL?style=social)](https://github.com/SalesforceAIResearch/UserRL) | Hierarchical | Conversation |
| [MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use](https://arxiv.org/abs/2508.18669) | [2025/08](https://github.com/zzwkk/MUA-RL) [![GitHub stars](https://img.shields.io/github/stars/zzwkk/MUA-RL?style=social)](https://github.com/zzwkk/MUA-RL) | Hierarchical | Conversation |
| [Magentic-UI: Towards Human-in-the-loop Agentic Systems](https://www.arxiv.org/abs/2507.22358) | [2025/07](https://github.com/microsoft/magentic-ui) [![GitHub stars](https://img.shields.io/github/stars/microsoft/magentic-ui?style=social)](https://github.com/microsoft/magentic-ui) | Hierarchical, Centralized | Conversation, Observation |
| [UserBench: An Interactive Gym Environment for User-Centric Agents](https://arxiv.org/abs/2507.22034) | [2025/07](https://github.com/SalesforceAIResearch/UserBench) [![GitHub stars](https://img.shields.io/github/stars/SalesforceAIResearch/UserBench?style=social)](https://github.com/SalesforceAIResearch/UserBench) | Decentralized | Conversation |
| [Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance](https://www.arxiv.org/abs/2507.17131) | [2025/07](https://github.com/yf-he/aria) [![GitHub stars](https://img.shields.io/github/stars/yf-he/aria?style=social)](https://github.com/yf-he/aria) | Hierarchical | Conversation |
| [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://arxiv.org/abs/2506.07982) | [2025/06](https://github.com/sierra-research/tau2-bench) [![GitHub stars](https://img.shields.io/github/stars/sierra-research/tau2-bench?style=social)](https://github.com/sierra-research/tau2-bench) | Decentralized | Conversation, Observation |
| [Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training](https://arxiv.org/abs/2406.00222) | [2025/05](https://github.com/google-research/google-research/tree/master/learning_to_clarify) | Decentralized | Conversation |
| [Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild](https://arxiv.org/abs/2505.16023) | [2025/05](https://github.com/microsoft/prototypical-hai-collaborations) [![GitHub stars](https://img.shields.io/github/stars/microsoft/prototypical-hai-collaborations?style=social)](https://github.com/microsoft/prototypical-hai-collaborations) | Centralized | Conversation |
| [XtraGPT: LLMs for Human-AI Collaboration on Controllable Academic Paper Revision](https://arxiv.org/abs/2505.11336) | [2025/05](https://github.com/NuoJohnChen/XtraGPT) [![GitHub stars](https://img.shields.io/github/stars/NuoJohnChen/XtraGPT?style=social)](https://github.com/NuoJohnChen/XtraGPT) | Centralized | Conversation |
| [MineWorld: A Real-Time and Open-Source Interactive World Model on Minecraft](https://arxiv.org/abs/2504.08388) | [2025/04](https://github.com/microsoft/MineWorld) [![GitHub stars](https://img.shields.io/github/stars/microsoft/MineWorld?style=social)](https://github.com/microsoft/MineWorld) | Decentralized | Conversation |
| [Experimental Exploration: Investigating Cooperative Interaction Behavior Between Humans and Large Language Model Agents](https://arxiv.org/abs/2503.07320) | [2025/03](https://arxiv.org/abs/2503.07320) | Decentralized | Conversation |
| [FinArena: A Human-Agent Collaboration Framework for Financial Market Analysis and Forecasting](https://arxiv.org/abs/2503.02692) | [2025/03](https://huggingface.co/datasets/Illogicaler/FinArena-low-cost-dataset) | Hierarchical | Conversation |
| [SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks](https://arxiv.org/abs/2503.15478) | [2025/03](https://github.com/facebookresearch/sweet_rl) [![GitHub stars](https://img.shields.io/github/stars/facebookresearch/sweet_rl?style=social)](https://github.com/facebookresearch/sweet_rl) | Decentralized | Conversation |
| [ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments](https://arxiv.org/abs/2502.19852) | [2025/02](https://github.com/stovecat/convcodeworld) [![GitHub stars](https://img.shields.io/github/stars/stovecat/convcodeworld?style=social)](https://github.com/stovecat/convcodeworld) | Decentralized | Conversation |
| [Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration](https://arxiv.org/abs/2502.11882) | [2025/02](https://github.com/sjtu-marl/DPT-Agent) [![GitHub stars](https://img.shields.io/github/stars/sjtu-marl/DPT-Agent?style=social)](https://github.com/sjtu-marl/DPT-Agent) | Decentralized | Observation |
| [CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigation](https://arxiv.org/abs/2501.16609) | [2025/01](https://oaishi.github.io/cowpilot.html) | Decentralized | Conversation |
| [Towards Modeling Human-Agentic Collaborative Workflows: A BPMN Extension](https://arxiv.org/abs/2412.05958) | [2024/12](https://github.com/BESSER-PEARL/agentic-bpmn) [![GitHub stars](https://img.shields.io/github/stars/BESSER-PEARL/agentic-bpmn?style=social)](https://github.com/BESSER-PEARL/agentic-bpmn) | Decentralized | Conversation |
| [Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration (Co-Gym)](https://arxiv.org/abs/2412.15701) | [2024/12](https://github.com/SALT-NLP/collaborative-gym) [![GitHub stars](https://img.shields.io/github/stars/SALT-NLP/collaborative-gym?style=social)](https://github.com/SALT-NLP/collaborative-gym) | Decentralized | Conversation |
| [To Help or Not to Help: LLM-based Attentive Support for Human-Robot Group Interactions](https://ieeexplore.ieee.org/abstract/document/10801517) | [2024/10](https://github.com/HRI-EU/AttentiveSupport) [![GitHub stars](https://img.shields.io/github/stars/HRI-EU/AttentiveSupport?style=social)](https://github.com/HRI-EU/AttentiveSupport) | Decentralized | Observation |
| [PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-Agent Tasks](https://openreview.net/forum?id=T5QLRRHyL1) | [2024/10](https://github.com/facebookresearch/partnr-planner/tree/main/) [![GitHub stars](https://img.shields.io/github/stars/facebookresearch/partnr-planner?style=social)](https://github.com/facebookresearch/partnr-planner/tree/main/) | Decentralized | Conversation |
| [AssistantX: An LLM-Powered Proactive Assistant in Collaborative Human-Populated Environment](https://arxiv.org/abs/2409.17655) | [2024/09](https://github.com/AssistantX-Agent/AssistantX) [![GitHub stars](https://img.shields.io/github/stars/AssistantX-Agent/AssistantX?style=social)](https://github.com/AssistantX-Agent/AssistantX) | Decentralized | Message Pool |
| [Mutual Theory of Mind in Human-AI Collaboration: An Empirical Study with LLM-driven AI Agents in a Real-time Shared Workspace Task](https://arxiv.org/abs/2409.08811) | [2024/09](https://arxiv.org/abs/2409.08811) | Decentralized | Conversation |
| [Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations](https://arxiv.org/abs/2408.15232) | [2024/08](https://github.com/stanford-oval/storm) [![GitHub stars](https://img.shields.io/github/stars/stanford-oval/storm?style=social)](https://github.com/stanford-oval/storm) | Decentralized | Conversation |
| [Human-LLM Collaboration in Generative Design for Customization](https://www.sciencedirect.com/science/article/abs/pii/S0278612525000731) | [2024/07](https://www.sciencedirect.com/science/article/abs/pii/S0278612525000731) | Decentralized | Conversation |
| [DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning](https://arxiv.org/abs/2406.11896) | [2024/06](https://github.com/DigiRL-agent/digirl) [![GitHub stars](https://img.shields.io/github/stars/DigiRL-agent/digirl?style=social)](https://github.com/DigiRL-agent/digirl) | Decentralized | Conversation |
| [Enhancing Human-Robot Collaborative Assembly in Manufacturing Systems Using Large Language Models](https://arxiv.org/abs/2406.01915) | [2024/06](https://arxiv.org/abs/2406.01915) | Decentralized | Conversation |
| [Enhancing the LLM-Based Robot Manipulation Through Human-Robot Collaboration](https://ieeexplore.ieee.org/abstract/document/10561501) | [2024/06](https://ieeexplore.ieee.org/abstract/document/10561501) | Decentralized | Conversation |
| [WebCanvas: Benchmarking Web Agents in Online Environments](https://arxiv.org/pdf/2406.12373) | [2024/06](https://huggingface.co/datasets/iMeanAI/Mind2Web-Live) | Decentralized | Conversation |
| [REVECA: Adaptive Planning and Trajectory-based Validation in Cooperative Language Agents Using Information Relevance and Relative Proximity](https://arxiv.org/abs/2405.16751) | [2024/05](https://arxiv.org/abs/2405.16751) | Hierarchical | Observation |
| [A Human-Computer Collaborative Tool for Training a Single Large Language Model Agent into a Network through Few Examples](https://arxiv.org/abs/2404.15974) | [2024/04](https://arxiv.org/abs/2404.15974) | Decentralized | Conversation |
| [AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaboration](https://arxiv.org/abs/2404.11943) | [2024/04](https://github.com/AgentCoord/AgentCoord) [![GitHub stars](https://img.shields.io/github/stars/AgentCoord/AgentCoord?style=social)](https://github.com/AgentCoord/AgentCoord) | Decentralized | Conversation |
| [An LLM-based approach for Enabling Seamless Human-Robot Collaboration in Assembly](https://www.sciencedirect.com/science/article/pii/S000785062400012X) | [2024/04](https://www.sciencedirect.com/science/article/pii/S000785062400012X) | Centralized | Conversation |
| [Autonomous Evaluation and Refinement of Digital Agents](https://arxiv.org/abs/2404.06474) | [2024/04](https://github.com/Berkeley-NLP/Agent-Eval-Refine) [![GitHub stars](https://img.shields.io/github/stars/Berkeley-NLP/Agent-Eval-Refine?style=social)](https://github.com/Berkeley-NLP/Agent-Eval-Refine) | Decentralized | Conversation |
| [PDFChatAnnotator: A Human-LLM Collaborative Multi-Modal Data Annotation Tool for PDF-Format Catalogs](https://dl.acm.org/doi/abs/10.1145/3640543.3645174) | [2024/04](https://dl.acm.org/doi/abs/10.1145/3640543.3645174) | Decentralized | Conversation |
| [Embodied LLM Agents Learn to Cooperate in Organized Teams](https://arxiv.org/abs/2403.12482) | [2024/03](https://github.com/tobeatraceur/Organized-LLM-Agents) [![GitHub stars](https://img.shields.io/github/stars/tobeatraceur/Organized-LLM-Agents?style=social)](https://github.com/tobeatraceur/Organized-LLM-Agents) | Decentralized | Conversation |
| [Large Language Model-based Human-Agent Collaboration for Complex Task Solving](https://arxiv.org/abs/2402.12914) | [2024/02](https://github.com/XueyangFeng/ReHAC) [![GitHub stars](https://img.shields.io/github/stars/XueyangFeng/ReHAC?style=social)](https://github.com/XueyangFeng/ReHAC) | Decentralized | Conversation |
| [WebLINX: Real-World Website Navigation with Multi-Turn Dialogue](https://arxiv.org/abs/2402.05930) | [2024/02](https://github.com/McGill-NLP/WebLINX) [![GitHub stars](https://img.shields.io/github/stars/McGill-NLP/WebLINX?style=social)](https://github.com/McGill-NLP/WebLINX) | Decentralized | Conversation |
| [A2C: A Modular Multi-stage Collaborative Decision Framework for Human-AI Teams](https://arxiv.org/abs/2401.14432) | [2024/01](https://anonymous.4open.science/r/A2C/README.md) | Decentralized | Conversation |
| [Ask-before-Plan: Proactive Language Agents for Real-World Planning](https://arxiv.org/abs/2406.12639) | [2024/01](https://github.com/magicgh/Ask-before-Plan) [![GitHub stars](https://img.shields.io/github/stars/magicgh/Ask-before-Plan?style=social)](https://github.com/magicgh/Ask-before-Plan) | Centralized | Conversation |
| [LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination](https://arxiv.org/abs/2312.15224) | [2023/12](https://github.com/HosnLS/Hierarchical-Language-Agent) [![GitHub stars](https://img.shields.io/github/stars/HosnLS/Hierarchical-Language-Agent?style=social)](https://github.com/HosnLS/Hierarchical-Language-Agent) | Hierarchical | Conversation |
| [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://arxiv.org/abs/2310.11667) | [2023/10](https://arxiv.org/abs/2310.11667) | Centralized | Conversation |
| [Drive As You Speak: Enabling Human-Like Interaction With Large Language Models in Autonomous Vehicles](https://arxiv.org/abs/2309.10228) | [2023/09](https://arxiv.org/abs/2309.10228) | Centralized | Conversation |
| [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://arxiv.org/pdf/2309.10691) | [2023/09](https://xwang.dev/mint-bench/) | Decentralized | Conversation |
| [MindAgent: Emergent Gaming Interaction](https://arxiv.org/abs/2309.09971) | [2023/09](https://github.com/mindagent/mindagent) [![GitHub stars](https://img.shields.io/github/stars/mindagent/mindagent?style=social)](https://github.com/mindagent/mindagent) | Centralized | Conversation |
| [LLM-Based Human-Robot Collaboration Framework for Manipulation Tasks](https://arxiv.org/abs/2308.14972) | [2023/08](https://arxiv.org/abs/2308.14972) | Decentralized | Conversation |
| [MetaGPT: Meta Programming for a Multi-Agent Collaborative Framework](https://arxiv.org/abs/2308.00352) | [2023/08](https://github.com/geekan/MetaGPT) [![GitHub stars](https://img.shields.io/github/stars/geekan/MetaGPT?style=social)](https://github.com/geekan/MetaGPT) | Decentralized | Message Pool |
| [Building Cooperative Embodied Agents Modularly with Large Language Models](https://arxiv.org/abs/2307.02485) | [2023/07](https://arxiv.org/abs/2307.02485) | Decentralized | Conversation |
| [Embodied Task Planning with Large Language Models](https://arxiv.org/abs/2307.01848) | [2023/07](https://github.com/Gary3410/TaPA) [![GitHub stars](https://img.shields.io/github/stars/Gary3410/TaPA?style=social)](https://github.com/Gary3410/TaPA) | Decentralized | Conversation |
| [Improved Trust in Human-Robot Collaboration With ChatGPT](https://ieeexplore.ieee.org/abstract/document/10141597) | [2023/06](https://ieeexplore.ieee.org/abstract/document/10141597) | Decentralized | Conversation |
| [Investigating Agency of LLMs in Human-AI Collaboration Tasks](https://arxiv.org/abs/2305.12815) | [2023/05](https://arxiv.org/abs/2305.12815) | Decentralized | Conversation |
| [Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents through Help Feedback](https://arxiv.org/abs/2304.10750) | [2023/04](https://arxiv.org/abs/2304.10750) | Decentralized | Conversation |
| [PaLM-E: An Embodied Multimodal Language Model](https://openreview.net/forum?id=VTpHpqM3Cf&utm_campaign=The%20Batch&utm_source=hs_email&utm_medium=email&utm_content=284568789&_hsenc=p2ANqtz-9lsSL4nXMrOGBQqGoqktY5Yno_r9-nTOARZinDcgihFNqcOFEQb_MVtHKdpgI2AC3N8SrNW5PxcD0uxl4WeKcPJgUOgw) | [2023/03](https://palm-e.github.io) | Decentralized | Conversation |
| [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://dl.acm.org/doi/abs/10.1145/3491102.3517582) | [2021/10](https://dl.acm.org/doi/abs/10.1145/3491102.3517582) | Hierarchical | Conversation |

Contributions are welcome! If you have relevant papers, code, or insights, feel free to submit a request 🤗.

If you find this repository useful, please consider citing our papers 💕:

*The survey has been accepted to **ACL 2026**; the BibTeX below will be updated to the proceedings entry once it is available.*

```
@misc{zou2025llmbasedhumanagentcollaborationinteraction,
      title={LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey}, 
      author={Henry Peng Zou and Wei-Chieh Huang and Yaozu Wu and Yankai Chen and Chunyu Miao and Hoang Nguyen and Yue Zhou and Weizhi Zhang and Liancheng Fang and Langzhou He and Yangning Li and Dongyuan Li and Renhe Jiang and Xue Liu and Philip S. Yu},
      year={2025},
      eprint={2505.00753},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.00753}, 
}

@misc{zou2025collaborativeintelligencehumanagentsystems,
      title={A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy}, 
      author={Henry Peng Zou and Wei-Chieh Huang and Yaozu Wu and Chunyu Miao and Dongyuan Li and Aiwei Liu and Yue Zhou and Yankai Chen and Weizhi Zhang and Yangning Li and Liancheng Fang and Renhe Jiang and Philip S. Yu},
      year={2025},
      eprint={2506.09420},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2506.09420}, 
}
```

## ⭐ Star History

[![Star History Chart](https://api.star-history.com/svg?repos=HenryPengZou/Awesome-LLM-Based-Human-Agent-System-Papers&type=Date)](https://www.star-history.com/#HenryPengZou/Awesome-LLM-Based-Human-Agent-System-Papers&Date)

Awesome-Human-Agent-Collaboration-Interaction-Systems

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Awesome-Human-Agent-Collaboration-Interaction-Systems

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README