mlsanityData to 7 Oct 2026

Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection

arXiv 2606.02812 ↗First posted 1 Jun 2026cs.AI cs.CLcited by 0

On the map: LLM agents and tool use → Medical and scientific domain agents

also in 1 more
Abstract (arXiv)

Modeling patient trajectories from longitudinal electronic health records (EHRs) requires reasoning over sparse, noisy, and long-context multimodal sequences. Existing LLM-based multi-agent systems address context length but process patients in isolation, failing to mirror how clinicians leverage accumulated experience from similar prior cases. We present Traj-Evolve, a self-evolving multi-agent system with two complementary evolving mechanisms. First, an Experience Pool (ExPool) acts as a non-parametric memory, indexing rejection-sampled reasoning traces to retrieve similar patients as few-shot contexts. Second, multi-agent reinforcement learning (MARL) via reward-ranked fine-tuning parametrically optimizes inter-agent and agent-memory collaboration. A leave-one-out cross-retrieval strategy unifies the two, aligning training- and inference-time behavior under retrieval augmentation. On a lung cancer prediction task utilizing up to five years of multimodal EHRs, Traj-Evolve outperforms 9 strong baselines on the overall population and a challenging never-smoker population. Analysis of the evolving dynamics highlights three key findings: (1) expanding the ExPool shifts optimal retrieval from diverse to specific samples; (2) under MARL, the manager agent's prediction loss converges quickly while the worker agents' temporal reasoning continues to benefit from more verified patients; and (3) the two mechanisms are complementary on the predicted risk, where ExPool improves specificity while MARL improves sensitivity.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 22 of its 44 references that are in the map. First posted on arXiv 1 Jun 2026.

Builds on

22 of 44 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions28 Mar
  2. 2025MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultation18 Mar

Other references · 20

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  4. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  5. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  6. 2023RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignmentcited by 672
  7. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  8. 2025RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learningcited by 357
  9. 2016RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanismcited by 344
  10. 2024Nomic Embed: Training a Reproducible Long Context Text Embeddercited by 255
  11. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 201
  12. 2024Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answeringcited by 95
8 more
  1. 2025MARFT: Multi-Agent Reinforcement Fine-Tuningcited by 51
  2. 2025TIMER: Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Recordscited by 33
  3. 2025Clinical ModernBERT: An efficient and long context encoder for biomedical textcited by 26
  4. 2025Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Predictioncited by 11
  5. 2025MoMA: A Mixture-of-Multimodal-Agents Architecture for Enhancing Clinical Prediction Modellingcited by 7
  6. 2022Modelling Patient Trajectories Using Multimodal Informationcited by 2
  7. 2025ClinNoteAgents: An LLM Multi-Agent System for Predicting and Interpreting Heart Failure 30-Day Readmission from Clinical Notescited by 1
  8. 2026RadTimeline: Timeline Summarization for Longitudinal Radiological Lung Findingscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection
  2. 2025Traj-CoA: Patient Trajectory Modeling via Chain-of-Agents for Lung Cancer Risk Prediction
  3. 2026Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improve
  4. 2026SAGEAgent: A Self-Evolving Agent for Cost-Aware Modality Acquisition in Multimodal Survival Prediction
  5. 2025Cohort-Aware Agents for Individualized Lung Cancer Risk Prediction Using a Retrieval-Augmented Model Selection Framework
  6. 2026Toward Vibe Medicine: A Self-Evolving Multi-Agent Framework for Clinical Decision Support
  7. 2026From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoning
  8. 2026EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and Reuse