TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling

• URL: http://arxiv.org/abs/2505.17155v1
• Date: Thu, 22 May 2025 12:23:30 GMT
• Title: TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling
• Authors: Weizhe Lin, Xing Li, Zhiyuan Yang, Xiaojin Fu, Hui-Ling Zhen, Yaoyuan Wang, Xianzhi Yu, Wulong Liu, Xiaosong Li, Mingxuan Yuan,
• Abstract summary: Large Reasoning Models (LRMs) demonstrate exceptional capability in tackling complex mathematical, logical, and coding tasks.<n>We propose TrimR, a verifier-based, training-free, efficient framework for dynamic Chain-of-Thought (CoT) compression.
• Score: 20.980976778470247
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Reasoning Models (LRMs) demonstrate exceptional capability in tackling complex mathematical, logical, and coding tasks by leveraging extended Chain-of-Thought (CoT) reasoning. Test-time scaling methods, such as prolonging CoT with explicit token-level exploration, can push LRMs' accuracy boundaries, but they incur significant decoding overhead. A key inefficiency source is LRMs often generate redundant thinking CoTs, which demonstrate clear structured overthinking and underthinking patterns. Inspired by human cognitive reasoning processes and numerical optimization theories, we propose TrimR, a verifier-based, training-free, efficient framework for dynamic CoT compression to trim reasoning and enhance test-time scaling, explicitly tailored for production-level deployment. Our method employs a lightweight, pretrained, instruction-tuned verifier to detect and truncate redundant intermediate thoughts of LRMs without any LRM or verifier fine-tuning. We present both the core algorithm and asynchronous online system engineered for high-throughput industrial applications. Empirical evaluations on Ascend NPUs and vLLM show that our framework delivers substantial gains in inference efficiency under large-batch workloads. In particular, on the four MATH500, AIME24, AIME25, and GPQA benchmarks, the reasoning runtime of Pangu-R-38B, QwQ-32B, and DeepSeek-R1-Distill-Qwen-32B is improved by up to 70% with negligible impact on accuracy.

Related papers

• R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning [60.37610817226533]
  Chain-of-thought (CoT) reasoning encourages step-by-step intermediate reasoning during inference.<n>CoT introduces substantial computational overhead due to its reliance on autoregressive decoding over long token sequences.<n>We present R-Stitch, a token-level, confidence-based hybrid decoding framework that accelerates CoT inference.
  arXiv  Detail & Related papers  (2025-07-23T08:14:36Z)
• KAT-V1: Kwai-AutoThink Technical Report [50.84483585850113]
  We present Kwaipilot-AutoThink (KAT), an open-source 40B large language model developed to address the overthinking problem in reasoning-intensive tasks.<n>KAT dynamically switches between reasoning and non-reasoning modes based on task complexity.<n>We also propose Step-SRPO, a reinforcement learning algorithm that incorporates intermediate supervision into the GRPO framework.
  arXiv  Detail & Related papers  (2025-07-11T04:07:10Z)
• Reinforced Latent Reasoning for LLM-based Recommendation [83.18146814163308]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities in complex problem-solving tasks.<n>Existing methods typically rely on fine-tuning with explicit chain-of-thought (CoT) data.<n>In this work, we explore an alternative approach that shifts from explicit CoT reasoning to compact, information-dense latent reasoning.
  arXiv  Detail & Related papers  (2025-05-25T11:03:45Z)
• Let LLMs Break Free from Overthinking via Self-Braking Tuning [60.08396797526657]
  Large reasoning models (LRMs) have significantly enhanced their reasoning capabilities by generating longer chains of thought.<n>This performance gain comes at the cost of a substantial increase in redundant reasoning during the generation process.<n>We propose a novel framework, Self-Braking Tuning (SBT), which tackles overthinking from the perspective of allowing the model to regulate its own reasoning process.
  arXiv  Detail & Related papers  (2025-05-20T16:53:40Z)
• Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models [32.49420948390984]
  Large reasoning models (LRMs) typically suffer from "overthinking" problems.<n>We propose a simple yet efficient pipeline, ThoughtMani, to enable LRMs to bypass unnecessary intermediate steps.<n>We find that ThoughtMani enhances safety alignment by an average of 10%.
  arXiv  Detail & Related papers  (2025-04-18T11:07:19Z)
• SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning [14.020244011380063]
  SpecReason is a system that accelerates LRM inference.<n>It exploits the semantic flexibility of thinking tokens in preserving final-answer accuracy.<n>It achieves $1.4-3.0times$ speedup over vanilla LRM inference.
  arXiv  Detail & Related papers  (2025-04-10T16:05:19Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• START: Self-taught Reasoner with Tools [51.38785489790888]
  We introduce START (Self-Taught Reasoner with Tools), a tool-integrated long Chain-of-thought (CoT) reasoning LLM.<n> START is capable of performing complex computations, self-checking, exploring diverse methods, and self-ging.<n>It significantly outperforms the base QwQ-32B and achieves performance comparable to the state-of-the-art open-weight model R1-Distill-Qwen-32B.
  arXiv  Detail & Related papers  (2025-03-06T17:11:51Z)

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.