{
  "id": 19301750,
  "title": "SciMARS: Multi-Agent Recursive Self-Improvement for Closed-Loop Scientific Discovery",
  "url": "https://urgent.news/2026/11/09/scimars-multi-agent-recursive-self-improvement-for-closed-loop",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-09T15:20:32.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2611.12552v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "We propose SciMARS, a framework for recursive task-local adaptation of multi-agent harnesses in closed-loop scientific discovery. Multi-agent systems coordinate analysis, experimental design, and verification as scientific evidence evolves. However, two problems limit their effectiveness: (i) without shared memory, agents lose observations and repeat work; (ii) fixed role procedures, handoffs,…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}