AI RESEARCH
Think Outside the Policy: In-Context Steered Policy Optimization
arXiv CS.LG
•
ArXi:2510.26519v3 Announce Type: replace Existing Reinforcement Learning from Verifiable Rewards (RLVR) methods, such as Group Relative Policy Optimization (GRPO), have achieved remarkable progress in improving the reasoning capabilities of Large Reasoning Models (LRMs). However, they exhibit limited exploration due to reliance on on-policy rollouts which are confined to the current policy's distribution, resulting in narrow trajectory diversity.