PaceReasoner: Label-Free Learning to Answer Briefly from Long Reasoning
Extended chain-of-thought reasoning improves problem-solving performance but increases inference cost and latency, motivating more accurate answers with shorter reasoning. We introduce PaceReasoner, a label-free test-time reinforcement learning framework that uses a model's LONG responses to improve its SHORT-mode accu...
Chang-Guo Jia, Zhi-You Xiao, Xin-Bei Ma et al.
· 0 citations