arXiv 2610.23344 · cs.CL · 2026-10-16
Language Models Learn to Improve Language Models
Minhua Lin, Zijun Wang, Zewen Liu, Zhaotian Weng, Bing He, Zhan Shi, Benoit Dumoulin, Xiang Zhang 等 10 人
机构待核实
在最新榜 #377 本站收录于 2026-10-26
一句话要点
LM2LM 用强化学习训练大模型提出改进语言模型的方案；为避免每个提案都跑完整训练的高昂成本，改用更便宜的替代反馈，并处理策略偏向被高估提案导致替代反馈失真的问题。
LM2LM trains LLMs with RL to propose effective language-model improvements, using cheaper surrogate feedback instead of full training runs and addressing the unreliability that arises when policy optimization favors overestimated proposals.
阅读 arXiv 原文 PDF Hugging Face 讨论
主题与学科
同主题：大语言模型
- Jeva: System One Models from First Principles ▲371
- Post-Training Leaves Behavioral Shadows on Unrelated Decisions ▲273
- OmniEdu: Open Foundation Models for Learning and Teaching ▲240
- PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking ▲163
- MemT-1.0: Towards Memory-Native Evolution ▲143
同主题：强化学习
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents 2026-09-30 · ▲642
- The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation 2026-09-29 · ▲511
- Player-1: Learning to Play from Synthetic Experience 2026-10-14 · ▲347
- Scaling Properties of Same-Family On-Policy Distillation 2026-09-26 · ▲327
- DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models 2026-10-08 · ▲325
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。