AI RESEARCH
LamPO: A Lambda Style Policy Optimization for Reasoning Language Models
arXiv CS.CL
•
ArXi:2605.21235v1 Announce Type: new Reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving reasoning language models on tasks such as mathematics, coding, and scientific question answering. However, widely used group-relative objectives, such as GRPO, summarize each sampled group with scalar statistics and therefore discard fine-grained relational information among candidate responses. This weakens credit assignment under sparse outcome rewards, especially when multiple generated solutions differ only subtly in reasoning quality.