mlsanityData to 7 Oct 2026

Medical and scientific domain agents

902 papers9 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: clinical, medical, reasoning, framework, agent

Key facts. Medical and scientific domain agents: 902 papers on arXiv since 2023 (data through 7 Oct 2026). 69 of its 902 mapped papers (8%) cite “AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments” (2024, arXiv 2405.07960). 43 of its 902 mapped papers (5%) cite “Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents” (2024, arXiv 2405.02957). 49 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

49 new papers, 17 Sep – 7 Oct; 9 this week.

  1. This week · 9
  2. CircuitATLAS: Agentic reasoning over a systems neuroscience knowledge graph for target discovery in circuitopathies
  3. MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation
  4. ChartBmkAgent: Harness-Governed Multi-Agent Construction of Chart QA Benchmarks from Sparse Error-Taxonomy Specifications also fits: Web, search, and research agents
  5. PsyCIDRA: A Dual-Agent Framework for Psychiatric Interviewing and Diagnostic Reasoning
  6. MedPrune: Topology-Efficient Multimodal Multi-Agent Communication Evolution for Medical VQA Tasks
  7. From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?
  8. APOD: reasoning-guided agentic population ordinary differential equation discovery for pharmacological digital twins
  9. Bridging the Evidence-to-Execution Gap:A Reflective Agent for Multi-Objective Peptide Design
  10. MedicalHarness: A Controlled Evaluation of LLMs and Agent Harnesses on Medical Tasks
  11. Earlier · 40
  12. LifeLong Digital Twin: A Unified Modeling Paradigm and Agent Harness for Event-Driven Lifelong Health State Trajectories
All 49
  1. templar: agentic induction and evolution of standardized radiology reporting templates from large-scale clinical corpora
  2. MedImageOSWorld: Benchmarking GUI Agents for Medical Image Consoles also fits: Multimodal and embodied agents
  3. ARISE: Adaptive Agentic Reasoning with Image-grounded Self-Evaluation for Interpretable IBD Assessment
  4. Agentic discovery of blood biomarker from distilled private health records
  5. Toward a Locally Deployable Agentic Co-Scientist: Small-Model Planning for Early-Stage Drug Discovery
  6. RadOnc-Agent: An LLM-Orchestrated Framework for AI Workflows Across the Radiotherapy Care Pathway
  7. Trajectory-Derived Confidence for Reliable, Resource-Aware Clinical Text-to-SQL Agents
  8. A Guideline-Augmented Multi-Agent Framework for Schema-as-Code Biomedical Named Entity Recognition
  9. A Multi-Agent LLM Framework for Personalized Health Checkup Interpretation and Guidance
  10. From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoning
  11. EHR-RobustGym: Benchmarking and Training Agents for Robust Clinical Reasoning
  12. Personalized State-Transition-Aware Memory for Clinical Agents also fits: Agent memory systems
  13. PrivMeSA: Privacy-Aware Self-Evolving Multi-Agent System for Medicine via Local-Remote LLM Collaboration
  14. From Retrieval to Reasoning: Agentic Mechanism Prediction from Cell Painting Profiles
  15. ARCagent: An Adaptive Retrieval Calibration Agent for Clinical Question Answering
  16. AutoBCI: Forecast-Guided Agentic Neural Architecture Discovery for EEG-Based Brain--Computer Interfaces
  17. TMCS: Tool-Grounded Multi-Agent Reasoning for Compositional Chemical Problem Solving also fits: Educational agents and math problem solving
  18. M3OS: A Monte Carlo Graph Search-Orchestrated Multi-Agent LLM System for Evidence-Traced Molecular Optimization
  19. BIABench: Evaluating AI agents on real-world bioimage analysis tasks
  20. Nutri-ATLAS: Embodied Agent for Tabulated Lookup and Assistance for Smarter nutrition
  21. BioDyad: Synchronize Biomedical Discovery and Machine Learning Engineering
  22. MammoClaw: Towards Skill-Evolving Agent Harness for Breast Cancer Mammography Analysis
  23. MACBT: A Multi-Agent Cognitive Behavioral Therapy Decision Support System with Longitudinal Memory
  24. SMARtCARE: Privacy-Preserving Agentic AI Systems for Bounded-Autonomy Clinical Decision Support
  25. SkinAgent AI: A Safety-Grounded Multimodal Agentic Framework for Non-Diagnostic Skincare Support
  26. Driving Epidemic Models with AI Agents: the Epydemix Agent Framework
  27. BaseCamp --- An Agentic AI Framework for Automating DNA Sequencing Data Pipelines also fits: Web, search, and research agents
  28. MolDesignBench: Evaluating LLM-based Agent for Scenario-grounded Molecular Design also fits: Software engineering coding agents
  29. Discover, Falsify, Revise: Auditing Input-Use Claims from Source Code to Predictive Contribution in Agent-Discovered Cell Models
  30. Governed AI-Agent Coordination for Dementia Care: Architecture, Safety Contracts, and Evidence-Derived Workflow Verification
  31. ChatT2: An Adaptive Framework for Developing a Large Language Model-Based Agent for Natural Product Domain Research
  32. The AI Neuroscientist: An Interactive Agentic Interface for Neuroimaging Analysis
  33. Ascent: An Agentic System over the Model Context Protocol for Real-World Clinical Data Analysis
  34. A Task-Oriented Multi-Agent Framework for Complex Wearable Health Analysis
  35. MAC-RRG: Iterative Multi-Agent Collaboration for X-ray Radiology Report Generation
  36. An Agentic Just-in-Time Adaptive Intervention System for Personalized Sleep Support: Proof-of-Concept Study with N of 1 Data
  37. MaSCoD: A Multi-Agent Framework for Structural-Context-Guided Candidate Causal Graph Generation also fits: Web, search, and research agents
  38. LearnActCoder: Role-Aware Error Memory for Adaptive Clinical Coding Agents
  39. Large Language Model Agents for Evidence Based Genetic Disease Severity Classification

Foundations

Most cited by papers here

  1. AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments2024cited by 69 here
  2. Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents2024cited by 43 here
  3. MMedAgent: Learning to Use Medical Tools with Multi-modal Agent2024cited by 43 here
  4. AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator2024cited by 32 here
  5. MedAgent-Pro: Towards Evidence-based Multi-modal Medical Diagnosis via Reasoning Agentic Workflow2025cited by 26 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 88 here
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 72 here
  3. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 62 here
  4. 2023A Survey on Large Language Model based Autonomous Agentscited by 61 here
  5. 2024AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environmentscited by 69 here
  6. 2024MMedAgent: Learning to Use Medical Tools with Multi-modal Agentcited by 43 here
  7. 2025MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agentscited by 21 here
17 more it builds on, not in this chain
  1. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 50 here
  2. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 59 here
  3. 2023Gorilla: Large Language Model Connected with Massive APIscited by 22 here
  4. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 43 here
  5. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 32 here
  6. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 62 here
  7. 2023AgentBench: Evaluating LLMs as Agentscited by 19 here
  8. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 20 here
  9. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 26 here
  10. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 26 here
  11. 2024ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learningcited by 19 here
  12. 2024AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulatorcited by 32 here
  13. 2024Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agentscited by 43 here
  14. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 20 here
  15. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 22 here
  16. 2025A Survey of LLM-based Agents in Medicine: How far are we from Baymax?cited by 21 here
  17. 2025MedAgent-Pro: Towards Evidence-based Multi-modal Medical Diagnosis via Reasoning Agentic Workflowcited by 26 here

The 24 most cited of 1,263.

Browse

30 of 902, ranked 6–35

  1. 6MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents202521
  2. 7A Survey of LLM-based Agents in Medicine: How far are we from Baymax?202521
  3. 8TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools202519
  4. 9ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning202419
  5. 10CACTUS: Chemistry Agent Connecting Tool-Usage to Science202419
  6. 11Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions202517
  7. 12El Agente: An Autonomous Agent for Quantum Chemistry202517
  8. 13BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology202515
  9. 14An Agentic System for Rare Disease Diagnosis with Traceable Reasoning202514
  10. 15DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation202514
All 30
  1. 16MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks202513
  2. 17AgentMD: Empowering Language Agents for Risk Prediction with Large-Scale Clinical Tool Learning202413
  3. 18MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning202512
  4. 19Evidence-based diagnostic reasoning with multi-agent copilot for human pathology202512
  5. 20CRISPR-GPT for Agentic Automation of Gene-editing Experiments202412
  6. 21MEDCO: Medical Education Copilots Based on A Multi-Agent Framework202412
  7. 22ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration202412
  8. 23DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration202412
  9. 24PathFinder: A Multi-Modal Multi-Agent System for Medical Diagnostic Decision-Making Applied to Histopathology202511
  10. 25CellAgent: An LLM-driven Multi-Agent Framework for Automated Single-cell Data Analysis202411
  11. 26MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis202510
  12. 27MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultation202510
  13. 28Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learning202510
  14. 29BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments202410
  15. 30A Review of Large Language Models and Autonomous Agents in Chemistry202410
  16. 31PharmAgents: Building a Virtual Pharma with Large Language Model Agents20259
  17. 32FHIR-AgentBench: Benchmarking LLM Agents for Realistic Interoperable EHR Question Answering20259
  18. 33PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments20268
  19. 34TxGemma: Efficient and Agentic LLMs for Therapeutics20258
  20. 35DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery20258