2026
LONG CHAIN-OF-THOUGHT COMPRESSION VIA FINE-GRAINED GROUP POLICY OPTIMIZATION
ICASSP 2026poster
Large Language Models (LLMs) often generate unnecessarily verbose Chain-of-Thought (CoT) reasoning that increases computational costs and latency without proportional performance gains. In this paper, we propose Fine-grained Group policy Optimization (FGO), a Reinforcement Learning (RL) algorithm th…