Saved in:
Bibliographic Details
Main Authors: Sui, Yi, Li, Chaozhuo, Song, Dawei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.09150
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911581405708288
author Sui, Yi
Li, Chaozhuo
Song, Dawei
author_facet Sui, Yi
Li, Chaozhuo
Song, Dawei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_09150
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Think Less, Know More: State-Aware Reasoning Compression with Knowledge Guidance for Efficient Reasoning
Sui, Yi
Li, Chaozhuo
Song, Dawei
Computation and Language
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.
title Think Less, Know More: State-Aware Reasoning Compression with Knowledge Guidance for Efficient Reasoning
topic Computation and Language
url https://arxiv.org/abs/2604.09150