{
  "id": 12312,
  "url": "https://arxiv.org/abs/2607.07820",
  "title": "DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment",
  "summary": "Training tool-use agents to improve from their own experience remains challenging, as supervised fine-tuning relies on fixed teacher-distilled trajectories, while sparse-reward reinforcement learning provides weak supervision for long-horizon interactions. We present DeepSearch-Evolve, a self-distillation framework for web agents built on DeepSearch-World, a deterministic and verifiable environment with reproducible search and page-reading tools. DeepSearch-World contains 420K multi-hop QA tasks",
  "authors": "Xinyu Geng, Xuanhua He, Sixiang Chen, Yanjing Xiao, Fan Zhang, Shijue Huang",
  "category": "research",
  "topics": "agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-07T20:00:00.000Z",
  "fetched_at": "2026-07-22T05:10:49.469Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/12312",
  "original_url": "https://arxiv.org/abs/2607.07820",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}