一作ACL 2026Findings· Findings of ACL
Orchestrating Tokens and Sequences: Dynamic Hybrid Policy Optimization for RLVR
Zijun Min · Bingshuai Liu · Ante Wang · Long Zhang · Anxiang Zeng · Haibo Zhang · Jinsong Su
摘要
Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising framework for optimizing large language models in reasoning tasks. However, existing RLVR algorithms focus on different granularities, and each has complementary strengths and limitations. Group Relative Policy Optimization...