Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning

• URL: http://arxiv.org/abs/2603.00296v1
• Date: Fri, 27 Feb 2026 20:23:59 GMT
• Title: Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning
• Authors: Xintong Li, Sha Li, Rongmei Lin, Hongye Jin, Linwei Li, Hejie Cui, Sarah Zhang, Chia-Yuan Chang, Kewei Cheng, Besnik Fetahu, Priyanka Nigam, Jingbo Shang, Bing Yin,
• Abstract summary: Large reasoning models improve with more test-time computation, but often overthink, producing unnecessarily long chains-of-thought that raise cost without improving accuracy.<n>We propose Step-wise Adaptive Penalization (SWAP), a fine-grained framework that allocates length reduction across steps based on intrinsic contribution.
• Score: 66.22060690012512
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large reasoning models improve with more test-time computation, but often overthink, producing unnecessarily long chains-of-thought that raise cost without improving accuracy. Prior reinforcement learning approaches typically rely on a single outcome reward with trajectory-level length penalties, which cannot distinguish essential from redundant reasoning steps and therefore yield blunt compression. Although recent work incorporates step-level signals, such as offline pruning, supervised data construction, or verifier-based intermediate rewards, reasoning length is rarely treated as an explicit step-level optimization objective during RL. We propose Step-wise Adaptive Penalization (SWAP), a fine-grained framework that allocates length reduction across steps based on intrinsic contribution. We estimate step importance from the model's on-policy log-probability improvement toward the correct answer, then treat excess length as a penalty mass redistributed to penalize low-importance steps more heavily while preserving high-importance reasoning. We optimize with a unified outcome-process advantage within group-relative policy optimization. Extensive experiments demonstrate that SWAP reduces reasoning length by 64.3% on average while improving accuracy by 5.7% relative to the base model.

Related papers

• Constraint-Rectified Training for Efficient Chain-of-Thought [60.52883907721588]
  Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs)<n>While longer reasoning traces can improve answer quality and unlock abilities such as self-correction, they also incur high inference costs and often introduce redundant steps, known as overthinking.<n>Recent research seeks to develop efficient reasoning strategies that balance reasoning length and accuracy.
  arXiv  Detail & Related papers  (2026-02-13T02:13:45Z)
• APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards [61.52322047892064]
  Test-Time Scaling (TTS) has significantly enhanced the capabilities of Large Reasoning Models (LRMs)<n>We observe that LRMs frequently conduct repetitive self-verification without revision even after obtaining the final answer during the reasoning process.<n>We propose Anchor-based Process Reward (APR), a structure-aware reward shaping method that localizes the reasoning anchor and penalizes exclusively the post-anchor AST.
  arXiv  Detail & Related papers  (2026-01-31T14:53:20Z)
• Step Potential Advantage Estimation: Harnessing Intermediate Confidence and Correctness for Efficient Mathematical Reasoning [25.562101968892833]
  Reinforcement Learning with Verifiable Rewards (RLVR) elicits long chain-of-thought reasoning in large language models (LLMs)<n>Existing approaches improve RLVR via token-level entropy or sequence-level length control, but lack a semantically grounded, step-level measure of reasoning progress.<n>We propose Step Potential Advantage Estimation (SPAE), a fine-grained credit assignment method that amplifies potential gains, penalizes potential drops, and applies penalty after potential saturates to encourage timely termination.
  arXiv  Detail & Related papers  (2026-01-07T11:36:01Z)
• Correct, Concise and Complete: Multi-stage Training For Adaptive Reasoning [11.179446105672461]
  We propose a multi-stage efficient reasoning method that combines supervised fine-tuning and reinforcement learning.<n>Our approach reduces response length by an average of 28% for 8B models and 40% for 32B models.<n>It achieves a superior trade-off compared to more complex state-of-the-art efficient reasoning methods.
  arXiv  Detail & Related papers  (2026-01-06T12:31:51Z)
• DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching [54.98126916293868]
  Large Reasoning Models (LRMs) produce excessively long chain-of-thought traces that degrade accuracy.<n>We propose a model-agnostic decoding framework that sketches the reasoning space by branching at high-entropy tokens and applies early stopping to select the shortest completed reasoning path.<n>This approach approximates the optimal solution that enhances both efficiency and accuracy, without requiring additional training or supervision.
  arXiv  Detail & Related papers  (2025-11-01T17:41:28Z)
• DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization [37.96314154235252]
  We propose a novel framework that decouples the length-based learning signal of correct rollouts from incorrect ones.<n>With a 1.5B model, our method achieves 77% length reduction with only 1.1% performance loss on simple questions.
  arXiv  Detail & Related papers  (2025-10-06T04:18:13Z)
• SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control [5.224609066309358]
  Large reasoning models (LRMs) have exhibited remarkable reasoning capabilities through inference-time scaling.<n>Previous work has attempted to mitigate this issue by penalizing the overall length of generated samples during reinforcement learning.<n>We propose SmartThinker, a two-stage learnable framework designed to enable fine-grained control over the length of reasoning chains.
  arXiv  Detail & Related papers  (2025-07-06T11:21:47Z)
• ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation [74.37307916314407]
  We propose a framework dubbed ConciseHint, which continuously encourages the reasoning model to speak concisely.<n>Experiments on the state-of-the-art LRMs, including DeepSeek-R1 and Qwen-3 series, demonstrate that our method can effectively produce concise reasoning.
  arXiv  Detail & Related papers  (2025-06-23T16:20:44Z)
• Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models [68.96619605651155]
  Large reasoning models (LRMs) may drastically increase the output length due to overthinking.<n>We propose a dynamic optimization framework that segments model-generated reasoning paths into distinct thinking patterns.<n>Our method achieves up to a 12% accuracy improvement and reducing token usage from approximately 5,000 to 3,000 tokens.
  arXiv  Detail & Related papers  (2025-05-27T20:59:29Z)
• Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards [17.829990749622496]
  We propose an adaptive reward-shaping method for large language models.<n>Our method dynamically adjusts the trade-off between accuracy and response length based on model performance.<n> Experiments show that our approach consistently and dramatically reduces reasoning length while largely maintaining accuracy.
  arXiv  Detail & Related papers  (2025-05-23T18:44:46Z)
• Fractured Chain-of-Thought Reasoning [61.647243580650446]
  We introduce Fractured Sampling, a unified inference-time strategy that interpolates between full CoT and solution-only sampling.<n>We show that Fractured Sampling consistently achieves superior accuracy-cost trade-offs, yielding steep log-linear scaling gains in Pass@k versus token budget.
  arXiv  Detail & Related papers  (2025-05-19T11:30:41Z)

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.