Think Less, Know More: State-Aware Reasoning Compression with Knowledge Guidance for Efficient Reasoning

arXiv:2604.09150v1 Announce Type: new Abstract: 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, and lack fine-grained, step-level adaptation to redundancy and reasoning bias. Therefore, we propose State-Aware Reasoning Compression with Knowledge Guidance (STACK), a framework that performs step-wise CoT compression by explicitly modeling stage-specific redundancy sources and integrating with a retrieval-augmented guidance. STACK constructs online long-short contrastive samples and dynamically switches between knowledge-guided compression for uncertain or biased reasoning state and self-prompted compression for overly long but confident state, complemented by an answer-convergence-based early stopping mechanism to suppress redundant verification. We further propose a reward-difference-driven training strategy by combining Proximal Policy Optimization (PPO) and Direct Preference Optimization (DPO), enabling models to learn state-conditioned compression strategies. Experiments on three mathematical reasoning benchmarks show that STACK achieves a superior accuracy-efficiency balance, reducing average response length by 59.9% while improving accuracy by 4.8 points over existing methods.

Related

• Reinforcement-aware Knowledge Distillation for LLM Reasoning
• Large Reasoning Models Learn Better Alignment from Flawed Thinking
• Chain-in-Tree: Back to Sequential Reasoning in LLM Tree Search
• Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models
• SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks

Source: arXiv cs.CL | 2026-04-13