{
  "id": 17777,
  "url": "https://arxiv.org/abs/2608.05219",
  "title": "When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents",
  "summary": "Privileged on-policy distillation provides dense supervision for multi-turn agents by allowing a synchronized teacher to re-score the student's response at every turn with access to training-only references, such as successful trajectories. In interactive environments, however, the student's preceding actions continually change the execution state. As the student takes different actions or completes subgoals in a different order, its rollout may reach states not covered by the reference, making",
  "authors": "Junzhuo Liu, Weiwei Li, Jun Ling, Peng Wang",
  "category": "research",
  "topics": "regulation,safety-alignment,children-education,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-04T20:00:00.000Z",
  "fetched_at": "2026-08-10T05:10:00.488Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/17777",
  "original_url": "https://arxiv.org/abs/2608.05219",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}