{
  "id": 5210,
  "url": "https://arxiv.org/abs/2604.27045v1",
  "title": "Detecting Clinical Discrepancies in Health Coaching Agents: A Dual-Stream Memory and Reconciliation Architecture",
  "summary": "As Large Language Model (LLM) agents transition from single-session tools to persistent systems managing longitudinal healthcare journeys, their memory architectures face a critical challenge: reconciling two imperfect sources of truth. The patient's evolving self-report is current but prone to recall bias, while the Electronic Health Record (EHR) is medically validated but frequently stale. General-purpose agent memory systems optimize for coherence by overwriting older facts with the user's la",
  "authors": "Samuel L Pugh, Eric Yang, Alexander Muir Sutherland, Alessandra Breschi",
  "category": "research",
  "topics": "bias-fairness,healthcare,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-29T17:59:28.000Z",
  "fetched_at": "2026-07-14T16:31:35.574Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5210",
  "original_url": "https://arxiv.org/abs/2604.27045v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}