{"slug": "traj-evolve-a-self-evolving-multi-agent-system-for-patient-trajectory-modeling", "title": "Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection", "summary": "Researchers have developed Traj-Evolve, a self-evolving multi-agent system that models patient trajectories from electronic health records by using an experience pool and multi-agent reinforcement learning to mimic how clinicians learn from prior cases. In a lung cancer early detection task using up to five years of multimodal data, the system outperformed nine strong baselines across the overall population and a never-smoker subgroup. The system's dual mechanisms proved complementary, with the experience pool improving specificity and reinforcement learning improving sensitivity.", "body_md": "arXiv:2606.02812v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/traj-evolve-a-self-evolving-multi-agent-system-for-patient-trajectory-modeling", "canonical_source": "https://arxiv.org/abs/2606.02812", "published_at": "2026-06-03 04:00:00+00:00", "updated_at": "2026-06-03 04:17:02.272482+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-agents"], "entities": ["Traj-Evolve", "Experience Pool", "ExPool", "MARL", "EHRs", "LLM"], "alternates": {"html": "https://wpnews.pro/news/traj-evolve-a-self-evolving-multi-agent-system-for-patient-trajectory-modeling", "markdown": "https://wpnews.pro/news/traj-evolve-a-self-evolving-multi-agent-system-for-patient-trajectory-modeling.md", "text": "https://wpnews.pro/news/traj-evolve-a-self-evolving-multi-agent-system-for-patient-trajectory-modeling.txt", "jsonld": "https://wpnews.pro/news/traj-evolve-a-self-evolving-multi-agent-system-for-patient-trajectory-modeling.jsonld"}}