一作ACL 2026Findings· Findings of ACL
Think Less, Know More: State-Aware Reasoning Compression with Knowledge Guidance for Efficient Reasoning
Yi Sui · Chaozhuo Li · Dawei Song
摘要
Large Reasoning Models (LRMs) achieve strong performance on complex tasks by leveraging long Chain-of-Thought (CoT), but often suffer from overthinking, leading to excessive reasoning steps and high inference latency. Existing CoT compression methods struggle to balance accuracy and efficiency, a...