# Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration

arXiv: https://arxiv.org/abs/2412.15701 · HTML: https://mlsanity.com/paper/2412.15701/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 20 Dec 2024.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 21 of 21)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?](https://mlsanity.com/paper/2403.07718/) (2024)
- [MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use](https://mlsanity.com/paper/2310.03128/) (2023)
- [PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action](https://mlsanity.com/paper/2409.00138/) (2024)
- [Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models](https://mlsanity.com/paper/2402.14207/) (2024)
- [On the Tool Manipulation Capability of Open-source Large Language Models](https://mlsanity.com/paper/2305.16504/) (2023)
- [AutoSurvey: Large Language Models Can Automatically Write Surveys](https://mlsanity.com/paper/2406.10252/) (2024)
- [When combinations of humans and AI are useful: A systematic review and meta-analysis](https://mlsanity.com/paper/2405.06087/) (2024)
- [USimAgent: Large Language Models for Simulating Search Users](https://mlsanity.com/paper/2403.09142/) (2024)
- [Long-Term Planning and Situational Awareness in OpenAI Five](https://mlsanity.com/paper/1912.06721/) (2019)
- [On the Perception of Difficulty: Differences between Humans and AI](https://mlsanity.com/paper/2304.09803/) (2023)

## Built on by (most cited first, 30 of 65)

- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety](https://mlsanity.com/paper/2507.06134/) (2025)
- [Levels of Autonomy for AI Agents](https://mlsanity.com/paper/2506.12469/) (2025)
- [Magentic-UI: Towards Human-in-the-loop Agentic Systems](https://mlsanity.com/paper/2507.22358/) (2025)
- [MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering](https://mlsanity.com/paper/2505.07782/) (2025)
- [Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations](https://mlsanity.com/paper/2601.17087/) (2026)
- [Future of Work with AI Agents: Auditing Automation and Augmentation Potential across the U.S. Workforce](https://mlsanity.com/paper/2506.06576/) (2025)
- [ChatBench: From Static Benchmarks to Human-AI Evaluation](https://mlsanity.com/paper/2504.07114/) (2025)
- [LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey](https://mlsanity.com/paper/2505.00753/) (2025)
- [LLM Agents Should Employ Security Principles](https://mlsanity.com/paper/2505.24019/) (2025)
- [Sparks of Science: Hypothesis Generation Using Structured Paper Data](https://mlsanity.com/paper/2504.12976/) (2025)
- [MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science](https://mlsanity.com/paper/2506.04405/) (2025)
- [CooperBench: Why Coding Agents Cannot be Your Teammates Yet](https://mlsanity.com/paper/2601.13295/) (2026)
- [Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs](https://mlsanity.com/paper/2511.19773/) (2025)
- [Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight](https://mlsanity.com/paper/2509.10723/) (2025)
- [When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation](https://mlsanity.com/paper/2604.00892/) (2026)
- [CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding](https://mlsanity.com/paper/2512.04111/) (2025)
- [From Replication to Redesign: Exploring Pairwise Comparisons for LLM-Based Peer Review](https://mlsanity.com/paper/2506.11343/) (2025)
- [Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration](https://mlsanity.com/paper/2502.11882/) (2025)
- [A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy](https://mlsanity.com/paper/2506.09420/) (2025)
- [MLE-Smith: Scaling MLE Tasks with Automated Multi-Agent Pipeline](https://mlsanity.com/paper/2510.07307/) (2025)
- [Multi-Actor Generative Artificial Intelligence as a Game Engine](https://mlsanity.com/paper/2507.08892/) (2025)
- [Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling](https://mlsanity.com/paper/2604.08178/) (2026)
- [Expert Preference-based Evaluation of Automated Related Work Generation](https://mlsanity.com/paper/2508.07955/) (2025)
- [When Should Users Check? Modeling Confirmation Frequency in Multi-Step Agentic AI Tasks](https://mlsanity.com/paper/2510.05307/) (2025)
- [Completion neq Collaboration: Scaling Collaborative Effort with Agents](https://mlsanity.com/paper/2510.25744/) (2025)
- [Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologies](https://mlsanity.com/paper/2510.22095/) (2025)
- [Modeling Distinct Human Interaction in Web Agents](https://mlsanity.com/paper/2602.17588/) (2026)
- [Revisable by Design: A Theory of Streaming LLM Agent Execution](https://mlsanity.com/paper/2604.23283/) (2026)
- [When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration](https://mlsanity.com/paper/2506.05579/) (2025)

## Abstract (arXiv)

While the advancement of large language models has spurred the development of AI agents to automate tasks, numerous use cases inherently require agents to collaborate with humans due to humans' latent preferences, domain expertise, or the need for control. To facilitate the study of human-agent collaboration, we introduce Collaborative Gym (Co-Gym), an open framework for developing and evaluating collaborative agents that engage in bidirectional communication with humans while interacting with task environments. We describe how the framework enables the implementation of new task environments and coordination between humans and agents through a flexible, non-turn-taking interaction paradigm, along with an evaluation suite that assesses both collaboration outcomes and processes. Our framework provides both a simulated condition with a reliable user simulator and a real-world condition with an interactive web application. Initial benchmark experiments across three representative tasks -- creating travel plans, writing related work sections, and analyzing tabular data -- demonstrate the benefits of human-agent collaboration: The best-performing collaborative agents consistently outperform their fully autonomous counterparts in task performance, achieving win rates of 86% in Travel Planning, 74% in Tabular Analysis, and 66% in Related Work when evaluated by real users. Despite these improvements, our evaluation reveals persistent limitations in current language models and agents, with communication and situational awareness failures observed in 65% and 40% of cases in the real condition, respectively. Released under the permissive MIT license, Co-Gym supports the addition of new task environments and can be used to develop collaborative agent applications, while its evaluation suite enables assessment and improvement of collaborative agents.