arXiv 2610.29458 · cs.LG · 2026-10-21
Harness Scaling for Generalizable Agentic Reinforcement Learning
Fei Bai, Huatong Song, Chuan Hao, Ran Tao, Jian Yang, Bryan Dai, Wayne Xin Zhao, Ji-Rong Wen
Renmin University of China
在最新榜 #350 本站收录于 2026-10-24
一句话要点
人民大学提出“执行框架扩展”（Harness Scaling）作为智能体强化学习的新扩展维度：不再只在单一固定框架里训练，而是在多样的工具使用、上下文管理等执行配置上训练，提升在不同框架间的迁移泛化。
Renmin University proposes Harness Scaling as a new scaling dimension for agentic RL: training across diverse execution configurations for tool use and context management instead of a single fixed harness, to improve transfer across harness setups.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库
主题与学科
同主题：强化学习
- Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation ▲214
- Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight ▲189
- LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches ▲152
- Sharpening Tax in Post-Training ▲111
- RULER: Instance-aware Rubric Rewards for SVG Generation ▲104
同主题：智能体
- Raven: The Harness of Harnesses for Composable Agentic Intelligence 2026-09-27 · ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents 2026-09-30 · ▲642
- Omni-IO Skills: Harnessing Your Agent Omni-Native 2026-09-25 · ▲485
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business 2026-10-14 · ▲388
- Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation 2026-10-14 · ▲364
同机构：Renmin University of China
- LoopVL: Recurrent Visual Intelligence 2026-09-29
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。