Mitigating Overthinking through Reasoning Shaping

• URL: http://arxiv.org/abs/2510.09535v1
• Date: Fri, 10 Oct 2025 16:49:03 GMT
• Title: Mitigating Overthinking through Reasoning Shaping
• Authors: Feifan Song, Shaohang Wei, Bofei Gao, Yejie Wang, Wen Luo, Wei Li, Linli Yao, Weimin Xiong, Liang Chen, Tianyu Liu, Houfeng Wang,
• Abstract summary: Group Relative Segment Penalization (GRSP) is a step-level method to regularize reasoning.<n>GRSP achieves superior token efficiency without heavily compromising accuracy.
• Score: 39.521132754190155
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large reasoning models (LRMs) boosted by Reinforcement Learning from Verifier Reward (RLVR) have shown great power in problem solving, yet they often cause overthinking: excessive, meandering reasoning that inflates computational cost. Prior designs of penalization in RLVR manage to reduce token consumption while often harming model performance, which arises from the oversimplicity of token-level supervision. In this paper, we argue that the granularity of supervision plays a crucial role in balancing efficiency and accuracy, and propose Group Relative Segment Penalization (GRSP), a step-level method to regularize reasoning. Since preliminary analyses show that reasoning segments are strongly correlated with token consumption and model performance, we design a length-aware weighting mechanism across segment clusters. Extensive experiments demonstrate that GRSP achieves superior token efficiency without heavily compromising accuracy, especially the advantages with harder problems. Moreover, GRSP stabilizes RL training and scales effectively across model sizes.

Related papers

• ATTNPO: Attention-Guided Process Supervision for Efficient Reasoning [31.958298572740848]
  We propose ATTNPO, a low-overhead process-supervised RL framework.<n>We first identify a set of special attention heads that naturally focus on essential steps while suppressing redundant ones.<n>We then employ two sub-strategies to mitigate overthinking by discouraging redundant steps while preserving accuracy by reducing penalties on essential steps.
  arXiv  Detail & Related papers  (2026-02-10T16:40:22Z)
• Does Your Reasoning Model Implicitly Know When to Stop Thinking? [45.954548163594204]
  We show that LRMs implicitly know the appropriate time to stop thinking, while this capability is obscured by current sampling paradigms.<n>Motivated by this, we introduce SAGE, a novel sampling paradigm that unleashes this efficient reasoning potential.
  arXiv  Detail & Related papers  (2026-02-09T07:38:22Z)
• Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning [34.10133693878611]
  We propose a multi-agent RL framework that selectively penalizes redundant chunks, while preserving essential reasoning logic.<n>Our framework, Self-Compression via MARL (SCMA), instantiates redundancy detection and evaluation through two specialized agents.<n> Empirical evaluations across model scales demonstrate that SCMA reduces response length by 11.1% to 39.0% while boosting accuracy by 4.33% to 10.02%.
  arXiv  Detail & Related papers  (2026-01-29T16:13:10Z)
• Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning [49.22815446849924]
  Large Language Models (LLMs) often struggle with problems that require multi-step reasoning.<n>For small-scale open-source models, Reinforcement Learning with Verifiable Rewards (RLVR) fails when correct solutions are rarely sampled.<n>We propose Supervised Reinforcement Learning (SRL), a framework that reformulates problem solving as generating a sequence of logical "actions"
  arXiv  Detail & Related papers  (2025-10-29T22:05:08Z)
• Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling [41.834250664485666]
  Large reasoning models generate excessively long reasoning paths without any performance benefit.<n>Existing solutions that penalize length often fail, inducing performance degradation.<n>We introduce a novel framework, DECS, built on our theoretical discovery of two previously unaddressed flaws in current length rewards.
  arXiv  Detail & Related papers  (2025-09-30T06:04:43Z)
• 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)
• Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement [101.77467538102924]
  Large reasoning models (LRMs) exhibit overthinking, which hinders efficiency and inflates inference cost.<n>We propose two lightweight methods to enhance LRM efficiency.<n>First, we introduce Efficiency Steering, a training-free activation steering technique that modulates reasoning behavior via a single direction.<n>Second, we develop Self-Rewarded Efficiency RL, a reinforcement learning framework that dynamically balances task accuracy and brevity.
  arXiv  Detail & Related papers  (2025-06-18T17:18:12Z)
• Scalable Chain of Thoughts via Elastic Reasoning [61.75753924952059]
  Elastic Reasoning is a novel framework for scalable chain of thoughts.<n>It separates reasoning into two phases--thinking and solution--with independently allocated budgets.<n>Our approach produces more concise and efficient reasoning even in unconstrained settings.
  arXiv  Detail & Related papers  (2025-05-08T15:01:06Z)
• Concise Reasoning via Reinforcement Learning [13.657506042120167]
  We revisit the core principles of reinforcement learning (RL)<n>We uncover a natural correlation between conciseness and accuracy that has been largely overlooked.<n>We show that introducing a secondary phase of RL training, using a very small set of problems, can significantly reduce chains of thought.
  arXiv  Detail & Related papers  (2025-04-07T15:35:54Z)
• SEAL: Steerable Reasoning Calibration of Large Language Models for Free [58.190800043449336]
  Large Language Models (LLMs) have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism.<n>Recent studies reveal substantial redundancy in the CoT reasoning traces, which negatively impacts model performance.<n>We introduce SEAL, a training-free approach that seamlessly calibrates the CoT process, improving accuracy while demonstrating significant efficiency gains.
  arXiv  Detail & Related papers  (2025-04-07T02:42:07Z)
• Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models [49.61246073215651]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks.<n>Recent advancements in OpenAI o1 and DeepSeek-R1 have further improved performance in System-2 reasoning domains.<n>However, they also introduce significant computational overhead due to verbose and redundant outputs.
  arXiv  Detail & Related papers  (2025-03-20T17:59:38Z)

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.