{
  "id": 3268,
  "url": "https://arxiv.org/abs/2606.02812v1",
  "title": "Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection",
  "summary": "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-p",
  "authors": "Sihang Zeng, Matthew Thompson, Ruth Etzioni, Meliha Yetisgen",
  "category": "research",
  "topics": "healthcare,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-01T19:30:07.000Z",
  "fetched_at": "2026-07-14T16:30:09.958Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3268",
  "original_url": "https://arxiv.org/abs/2606.02812v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}