{
  "id": 10995,
  "url": "https://arxiv.org/abs/2607.14777",
  "title": "SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning",
  "summary": "Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn interaction, tool use, and environment feedback. Outcome-based reinforcement learning (RL) provides a practical optimization paradigm, but its sparse trajectory-level rewards offer limited guidance on intermediate decisions, leaving a supervision gap between episode-level outcomes and token-level policy learning. We propose SEED (SElf-Evolving On-Policy Distillation), a self-evolving ",
  "authors": "Jinyang Wu, Shuo Yang, Zhengxi Lu, Fan Zhang, Yuhao Shen, Lang Feng",
  "category": "research",
  "topics": "regulation,agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-15T20:00:00.000Z",
  "fetched_at": "2026-07-17T05:10:53.887Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/10995",
  "original_url": "https://arxiv.org/abs/2607.14777",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}