{
  "id": 4465,
  "url": "https://arxiv.org/abs/2605.12070v2",
  "title": "Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction",
  "summary": "Asynchronous reinforcement learning improves rollout throughput for large language model agents by decoupling sample generation from policy optimization, but it also introduces a critical failure mode for PPO-style off-policy correction. In heterogeneous training systems, the total importance ratio should ideally be decomposed into two semantically distinct factors: a \\emph{training--inference discrepancy term} that aligns inference-side and training-side distributions at the same behavior-polic",
  "authors": "Zhong Guan, Yongjian Guo, Haoran Sun, Wen Huang, Shuai Di, Likang Wu et al.",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-12T12:57:55.000Z",
  "fetched_at": "2026-07-14T16:31:03.576Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4465",
  "original_url": "https://arxiv.org/abs/2605.12070v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}