{
  "id": 16222,
  "url": "https://arxiv.org/abs/2608.01837",
  "title": "PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning",
  "summary": "Large language model agents have shown strong potential in complex interactive tasks, yet their reinforcement learning (RL) is often hindered by sparse rewards, as a long multi-turn trajectory may receive only a single outcome-level signal. On-policy self-distillation (OPSD) provides dense token-level supervision from a privileged teacher, but the teacher may not be reliable at every position. Existing methods commonly rely on isolated token-level discrepancies, which can be sensitive to noise,",
  "authors": "Chunji Lv, Yangguang Wei, Junlin Liu, Yang Gao, Ming Liu, Xinming Wang",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-02T20:00:00.000Z",
  "fetched_at": "2026-08-05T05:10:44.550Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/16222",
  "original_url": "https://arxiv.org/abs/2608.01837",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}