3 papers
cs.CL2026
Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards
Mengjie Ren, Jie Lou, Boxi Cao +6
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language models. However, RLVR training…
cs.LG2026
Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning
Zichao Li, Jie Lou, Fangchen Dong +8
Reinforcement learning significantly enhances LLM capabilities but suffers from a critical issue: length inflation, where models adopt verbosity or inefficient reasoning to maximiz…
cs.CL2025
The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model
Jiawei Chen, Wentao Chen, Jing Su +6
Large language models (LLMs) have shown significant multilingual capabilities. However, the mechanisms underlying the development of these capabilities during pre-training are not…