{
  "id": 5804,
  "url": "https://arxiv.org/abs/2604.14518v2",
  "title": "Mind DeepResearch Technical Report",
  "summary": "We present Mind DeepResearch (MindDR), an efficient multi-agent deep research framework that achieves leading performance with only ~30B-parameter models through a meticulously designed data synthesis and multi-stage training pipeline. The core innovation of MindDR lies in a collaborative three-agent architecture (Planning Agent, DeepSearch Agent, and Report Agent) and a four-stage agent-specialized training pipeline comprising SFT cold-start, Search-RL, Report-RL and preference alignment. With ",
  "authors": "MindDR Team, Li Auto Inc",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-16T01:20:06.000Z",
  "fetched_at": "2026-07-14T16:32:02.059Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5804",
  "original_url": "https://arxiv.org/abs/2604.14518v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}