Entropy-Guided Reasoning Compression

• URL: http://arxiv.org/abs/2511.14258v2
• Date: Mon, 24 Nov 2025 10:36:50 GMT
• Title: Entropy-Guided Reasoning Compression
• Authors: Hourun Zhu, Yang Gao, Wenlong Fei, Jiawei Li, Huashan Sun,
• Abstract summary: We develop an entropy-guided training framework for large reasoning models.<n>As entropy descends, the model is guided toward efficient reasoning by encouraging concise thought steps.<n>Our method compresses reasoning length to 20% of the original while maintaining or even surpassing baseline accuracy.
• Score: 11.181525993239115
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large reasoning models have demonstrated remarkable performance on complex reasoning tasks, yet the excessive length of their chain-of-thought outputs remains a major practical bottleneck due to high computation cost and poor deployability. Existing compression methods have achieved partial success but overlook a crucial phenomenon in the training process -- the entropy conflict. During compression training, entropy decreases, leading to shorter reasoning but limited exploration, while accuracy-oriented objectives increase entropy, lengthening reasoning chains. This can cause the model to get stuck in a local dilemma. Our analysis further reveals the origin of the entropy conflict: many high-entropy tokens are logical connectors that receive larger gradients and are encouraged under the performance objective, while the compression objective simultaneously penalizes these potentially redundant connectors. This opposing pressure creates a direct source of entropy conflict. To address these issues, we adopt an entropy-guided training framework. As entropy descends, the model is guided toward efficient reasoning by encouraging concise thought steps; as entropy rises, exploration is reinforced under the compact reasoning mode to improve robustness. Experiments on six mathematical benchmarks show that our method compresses reasoning length to 20% of the original while maintaining or even surpassing baseline accuracy. Code and models will be released publicly.

Related papers

• Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning [39.72119774004103]
  Chain-of-Thought (CoT) has substantially empowered Large Language Models (LLMs) to tackle complex reasoning tasks.<n>The verbose nature of explicit reasoning steps incurs prohibitive inference latency and computational costs, limiting real-world deployment.<n>We propose Compress responses for Easy questions and Explore Hard ones (CEEH), a difficulty-aware approach to RL-based efficient reasoning.
  arXiv  Detail & Related papers  (2026-02-26T05:47:30Z)
• ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought [49.203970812338916]
  Explicit reasoning chains introduce substantial computational redundancy.<n>Recent latent reasoning methods attempt to mitigate this by compressing reasoning processes into latent space.<n>We propose Rendered CoT-Guided variational Latent Reasoning (ReGuLaR)
  arXiv  Detail & Related papers  (2026-01-30T17:08:06Z)
• DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference [68.05879215304641]
  Recent reasoning Large Language Models (LLMs) demonstrate remarkable problem-solving abilities but often generate long thinking traces whose utility is unclear.<n>Our work aims to improve their efficiency, enabling them to reach high performance without overthinking.<n>We introduce textbfDiffAdapt, a lightweight framework that selects Easy/Normal/Hard inference strategies per question based on their difficulty and reasoning trace entropy.
  arXiv  Detail & Related papers  (2025-10-22T15:16:06Z)
• PEAR: Phase Entropy Aware Reward for Efficient Reasoning [23.381346604897246]
  This paper introduces Phase Entropy Aware Reward (PEAR), a reward mechanism that incorporates phase-dependent entropy into the reward design.<n>Experiments across four benchmarks demonstrate that PEAR consistently reduces response length while sustaining competitive accuracy across model scales.
  arXiv  Detail & Related papers  (2025-10-09T10:04:31Z)
• Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation [82.62935304152239]
  Large Language Models (LLMs) have demonstrated remarkable reasoning abilities on complex problems using long Chain-of-Thought (CoT) reasoning.<n>They often suffer from overthinking, meaning generating unnecessarily lengthy reasoning steps for simpler problems.<n>We introduce a novel metric Token Entropy Cumulative Average (TECA), which measures the extent of exploration throughout the reasoning process.
  arXiv  Detail & Related papers  (2025-10-02T17:36:50Z)
• Measuring Reasoning Utility in LLMs via Conditional Entropy Reduction [3.9481110638616617]
  We measure the model's uncertainty on the answer span Y at each reasoning step using conditional entropy.<n>We also corroborate that incorrect reasoning paths tend to be longer than correct ones, suggesting that longer reasoning does not necessarily yield better outcomes.
  arXiv  Detail & Related papers  (2025-08-28T03:43:38Z)
• The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models [99.98293908799731]
  This paper aims to overcome a major obstacle in scaling RL for reasoning with LLMs, namely the collapse of policy entropy.<n>In practice, we establish a transformation equation R=-a*eH+b between entropy H and downstream performance R.<n>We propose two simple yet effective techniques, namely Clip-Cov and KL-Cov, which clip and apply KL penalty to tokens with high covariances respectively.
  arXiv  Detail & Related papers  (2025-05-28T17:38:45Z)
• Adaptive Deep Reasoning: Triggering Deep Thinking When Needed [28.575411507835973]
  Large language models (LLMs) have shown impressive capabilities in handling complex tasks through long-chain reasoning.<n>We propose a novel approach that autonomously switches between short and long-chain reasoning chains based on problem complexity.<n>This advancement enhances the practicality of reasoning in large language models for real-world applications.
  arXiv  Detail & Related papers  (2025-05-26T15:08:51Z)
• Entropy-Based Block Pruning for Efficient Large Language Models [81.18339597023187]
  We propose an entropy-based pruning strategy to enhance efficiency while maintaining performance.<n> Empirical analysis reveals that the entropy of hidden representations decreases in the early blocks but progressively increases across most subsequent blocks.
  arXiv  Detail & Related papers  (2025-04-04T03:42:34Z)
• Action Redundancy in Reinforcement Learning [54.291331971813364]
  We show that transition entropy can be described by two terms; namely, model-dependent transition entropy and action redundancy. Our results suggest that action redundancy is a fundamental problem in reinforcement learning.
  arXiv  Detail & Related papers  (2021-02-22T19:47:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.