mlsanityData to 14 Oct 2026

MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science

arXiv 2506.04405 ↗First posted 4 Jun 2025cs.CL cs.AI cs.LGcited by 23

On the map: LLM reasoning → Clinical and biomedical applications

also in 1 more
Abstract (arXiv)

We introduce MedAgentGym, a scalable and interactive training environment designed to enhance coding-based biomedical reasoning capabilities in large language model (LLM) agents. MedAgentGym comprises 72,413 task instances across 129 categories derived from 12 authentic real-world biomedical scenarios. Tasks are encapsulated within executable sandbox environments, each featuring detailed task specifications, interactive feedback mechanisms, verifiable ground truth annotations, and scalable training trajectory generation. Extensive benchmarking of 29 LLMs reveals substantial performance disparities in biomedical data science between commercial and open-source LLMs. Leveraging efficient multi-threaded and multi-turn trajectory sampling in MedAgentGym, Med-Copilot achieves performance gains of +43.02% and +45.28% from offline and online reinforcement learning, respectively, demonstrating MedAgentGym as an effective training ground while establishing itself as a cost-effective, privacy-preserving alternative competitive with proprietary LLMs (gpt-4o). By offering a unified execution environment with a comprehensive benchmark and accessible, extensible training resources, MedAgentGym delivers an integrated platform to develop LLM-based coding assistants for advanced biomedical data science.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 80 of its 114 references that are in the map. First posted on arXiv 4 Jun 2025.

Builds on

80 of 114 references.

Closest ancestors · 17

Same direction, newest first

  1. 2025MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning31 May
  2. 2025Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL23 May
  3. 2025MedCaseReasoning: Evaluating and learning diagnostic reasoning from clinical case reports16 May
  4. 2025Disentangling Reasoning and Knowledge in Medical Large Language Models16 May
  5. 2025ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model13 Apr
  6. 2025MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs1 Apr
  7. 2025m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning with Large Language Models1 Apr
  8. 2025Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models18 Mar
  9. 2025TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools14 Mar
  10. 2025MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks10 Mar
  11. 2025Med-RLVR: Emerging Medical Reasoning from a 3B base model via reinforcement Learning27 Feb
  12. 2024HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs25 Dec
5 more
  1. 2024MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning3 Jun
  2. 2024MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoning5 May
  3. 2024EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records13 Jan
  4. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning16 Nov
  5. 2022Can large language models reason about medical questions?17 Jul

Other references · 63

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  6. 2024Qwen2.5 Technical Reportcited by 4,942
  7. 2024GPT-4o System Cardcited by 4,588
  8. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  9. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  10. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  11. 2025Gemma 3 Technical Reportcited by 1,824
  12. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
38 more
  1. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
  2. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,288
  3. 2023AgentBench: Evaluating LLMs as Agentscited by 1,267
  4. 2024Qwen2.5-Coder Technical Reportcited by 1,203
  5. 2024Executable Code Actions Elicit Better LLM Agentscited by 564
  6. 2022MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answeringcited by 543
  7. 2024MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineeringcited by 469
  8. 2025HealthBench: Evaluating Large Language Models Towards Improved Human Healthcited by 429
  9. 2025RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learningcited by 386
  10. 2023MLAgentBench: Evaluating Language Agents on Machine Learning Experimentationcited by 366
  11. 2024WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?cited by 363
  12. 2024Training Software Engineering Agents and Verifiers with SWE-Gymcited by 336
  13. 2024Benchmarking Retrieval-Augmented Generation for Medicinecited by 331
  14. 2024OpenCodeInterpreter: Integrating Code Generation with Execution and Refinementcited by 247
  15. 2024Iterative Reasoning Preference Optimizationcited by 246
  16. 2024AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environmentscited by 231
  17. 2025MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understandingcited by 224
  18. 2024Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agentscited by 218
  19. 2024MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Makingcited by 163
  20. 2024The BrowserGym Ecosystem for Web Agent Researchcited by 161
  21. 2025REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewardscited by 130
  22. 2024DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoningcited by 125
  23. 2024DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?cited by 125
  24. 2025MLGym: A New Framework and Benchmark for Advancing AI Research Agentscited by 124
  25. 2019MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-IIIcited by 122
  26. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environmentscited by 120
  27. 2025Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolutioncited by 116
  28. 2024MMedAgent: Learning to Use Medical Tools with Multi-modal Agentcited by 109
  29. 2023EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Modelscited by 105
  30. 2025BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biologycited by 89
  31. 2025A Survey of LLM-based Agents in Medicine: How far are we from Baymax?cited by 85
  32. 2019Text-to-SQL Generation for Question Answering on Electronic Medical Recordscited by 77
  33. 2025AgentRxiv: Towards Collaborative Autonomous Researchcited by 72
  34. 2024MedCalc-Bench: Evaluating Large Language Models for Medical Calculationscited by 70
  35. 2023ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Codecited by 65
  36. 2024Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaborationcited by 65
  37. 2025DataSciBench: An LLM Agent Benchmark for Data Sciencecited by 57
  38. 2025SMART: Self-Aware Agent for Tool Overuse Mitigationcited by 52

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 17.

23 papers.

Sort:

By area:

  1. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 205
  2. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  3. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  4. 2025Building a Foundational Guardrail for General Agentic Systems via Synthetic Datacited by 29
  5. 2025Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMscited by 17
  6. 2026CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?cited by 8
  7. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  8. 2026HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agentscited by 8
  9. 2026MEDVISTAGYM: A Scalable Training Environment for Thinking with Medical Images via Tool-Integrated Reinforcement Learningcited by 4
  10. 2026Medical Reasoning with Large Language Models: A Survey and MR-Benchcited by 4
  11. 2026Healthcare AI GYM for Medical Agentscited by 4
  12. 2026Environment-Grounded Automated Prompt Optimization for LLM Game Agentscited by 3
11 more
  1. 2026Do LLMs Know What Is Private Internally? Probing and Steering Contextual Privacy Norms in Large Language Model Representationscited by 2
  2. 2026The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomycited by 2
  3. 2025From Conversation to Query Execution: Benchmarking User and Tool Interactions for EHR Database Agentscited by 1
  4. 2026PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documentscited by 1
  5. 2025Reliable Curation of EHR Dataset via Large Language Models under Environmental Constraintscited by 0
  6. 2026Benchmarking Agents in Insurance Underwriting Environmentscited by 0
  7. 2026From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environmentscited by 0
  8. 2026A Unified Benchmark for Dynamic Medical Treatment Reinforcement Learningcited by 0
  9. 2026Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistancecited by 0
  10. 2026ClinLens: Towards Long-Horizon Coding Agents for Longitudinal Multimodal Clinical Data Sciencecited by 0
  11. 2026OpenTumorBoard: A Real-World Benchmark of Multidisciplinary Tumor Board Discussion Trajectoriescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MedBrowseComp: Benchmarking Medical Deep Research and Computer Use
  2. 2026Meissa: Multi-modal Medical Agentic Intelligence
  3. 2025Knowledge-Driven Agentic Scientific Corpus Distillation Framework for Biomedical Large Language Models Training
  4. 2025MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents
  5. 2025MedAI: Evaluating TxAgent's Therapeutic Agentic Reasoning in the NeurIPS CURE-Bench Competition
  6. 2026Empowering Locally Deployable Medical Agent via State Enhanced Logical Skills for FHIR-based Clinical Tasks
  7. 2026Scaling Medical Reasoning Verification via Tool-Integrated Reinforcement Learning
  8. 2026SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents