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 and 2 more
Affiliation unverified
In latest · #377 Added on 2026-10-26
One-line takeaway
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.
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。
Read on arXiv PDF Hugging Face discussion
Topics & disciplines
More on LLMs
- 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
More on Reinforcement learning
- 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
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-26.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.