ReasonBridge: Efficient Reasoning Transfer from Closed to Open-Source Language Models

• URL: http://arxiv.org/abs/2506.22865v1
• Date: Sat, 28 Jun 2025 12:22:55 GMT
• Title: ReasonBridge: Efficient Reasoning Transfer from Closed to Open-Source Language Models
• Authors: Ziqi Zhong, Xunzhu Tang,
• Abstract summary: This paper introduces ReasonBridge, a methodology that efficiently transfers reasoning capabilities from powerful closed-source to open-source models.<n>We develop a tailored dataset Reason1K with only 1,000 carefully curated reasoning traces emphasizing difficulty, diversity, and quality.<n> Comprehensive evaluations demonstrate that ReasonBridge improves reasoning capabilities in open-source models by up to 23% on benchmark tasks.
• Score: 1.125423117145132
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advancements in Large Language Models (LLMs) have revealed a significant performance gap between closed-source and open-source models, particularly in tasks requiring complex reasoning and precise instruction following. This paper introduces ReasonBridge, a methodology that efficiently transfers reasoning capabilities from powerful closed-source to open-source models through a novel hierarchical knowledge distillation framework. We develop a tailored dataset Reason1K with only 1,000 carefully curated reasoning traces emphasizing difficulty, diversity, and quality. These traces are filtered from across multiple domains using a structured multi-criteria selection algorithm. Our transfer learning approach incorporates: (1) a hierarchical distillation process capturing both strategic abstraction and tactical implementation patterns, (2) a sparse reasoning-focused adapter architecture requiring only 0.3% additional trainable parameters, and (3) a test-time compute scaling mechanism using guided inference interventions. Comprehensive evaluations demonstrate that ReasonBridge improves reasoning capabilities in open-source models by up to 23% on benchmark tasks, significantly narrowing the gap with closed-source models. Notably, the enhanced Qwen2.5-14B outperforms Claude-Sonnet3.5 on MATH500 and matches its performance on competition-level AIME problems. Our methodology generalizes effectively across diverse reasoning domains and model architectures, establishing a sample-efficient approach to reasoning enhancement for instruction following.

Related papers

• 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)
• Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code [76.80306464249217]
  We propose TeaR, which aims at teaching LLMs to reason better.<n>TeaR leverages careful data curation and reinforcement learning to guide models in discovering optimal reasoning paths through code-related tasks.<n>We conduct extensive experiments using two base models and three long-CoT distillation models, with model sizes ranging from 1.5 billion to 32 billion parameters, and across 17 benchmarks spanning Math, Knowledge, Code, and Logical Reasoning.
  arXiv  Detail & Related papers  (2025-07-10T07:34:05Z)
• Boosting Open-Source LLMs for Program Repair via Reasoning Transfer and LLM-Guided Reinforcement Learning [7.850001507980097]
  Several closed-source LLMs have consistently outperformed open-source alternatives in program repair tasks.<n>This paper introduces Repairity, a novel three-stage methodology that significantly narrows this performance gap.
  arXiv  Detail & Related papers  (2025-06-04T13:13:58Z)
• Activation-Guided Consensus Merging for Large Language Models [25.68958388022476]
  We present textbfActivation-Guided textbfConsensus textbfMerging (textbfACM), a plug-and-play merging framework that determines layer-specific merging coefficients.<n>Experiments on Long-to-Short (L2S) and general merging tasks demonstrate that ACM consistently outperforms all baseline methods.
  arXiv  Detail & Related papers  (2025-05-20T07:04:01Z)
• 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)
• Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Models [4.737806982257592]
  This study proposes a knowledge distillation algorithm based on large language models and feature alignment.<n>The proposed model performs very close to the state-of-the-art GPT-4 model in terms of evaluation indicators such as perplexity, BLEU, ROUGE, and CER.
  arXiv  Detail & Related papers  (2024-12-27T04:37:06Z)
• A NotSo Simple Way to Beat Simple Bench [0.0]
  This paper presents a novel framework for enhancing reasoning capabilities in large language models (LLMs)<n>We propose a multi-step prompting strategy coupled with global consistency checks to improve model accuracy and robustness.<n>Our results reveal model-specific strengths: Claude excels in maintaining logical consistency, while GPT-4o exhibits exploratory creativity but struggles with ambiguous prompts.
  arXiv  Detail & Related papers  (2024-12-12T16:04:31Z)
• A Comparative Study on Reasoning Patterns of OpenAI's o1 Model [69.08287909042421]
  We show that OpenAI's o1 model has achieved the best performance on most datasets. We also provide a detailed analysis on several reasoning benchmarks.
  arXiv  Detail & Related papers  (2024-10-17T15:09:03Z)
• Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization [49.362750475706235]
  Reinforcement Learning (RL) plays a crucial role in aligning large language models with human preferences and improving their ability to perform complex tasks.<n>We introduce Direct Q-function Optimization (DQO), which formulates the response generation process as a Markov Decision Process (MDP) and utilizes the soft actor-critic (SAC) framework to optimize a Q-function directly parameterized by the language model.<n> Experimental results on two math problem-solving datasets, GSM8K and MATH, demonstrate that DQO outperforms previous methods, establishing it as a promising offline reinforcement learning approach for aligning language models.
  arXiv  Detail & Related papers  (2024-10-11T23:29:20Z)
• Advancing LLM Reasoning Generalists with Preference Trees [119.57169648859707]
  We introduce Eurus, a suite of large language models (LLMs) optimized for reasoning. Eurus models achieve state-of-the-art results among open-source models on a diverse set of benchmarks.
  arXiv  Detail & Related papers  (2024-04-02T16:25:30Z)
• CodingTeachLLM: Empowering LLM's Coding Ability via AST Prior Knowledge [0.0]
  We introduce CodingTeachLLM, a large language model (LLM) designed for coding teaching.<n>Our model realizes the structural disassembly and incremental guided output of educational knowledge.<n>Our model also achieves state-of-the-art in code abilities compared to open-source models.
  arXiv  Detail & Related papers  (2024-03-13T05:38:39Z)
• Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models [102.72940700598055]
  In reasoning tasks, even a minor error can cascade into inaccurate results. We develop a method that avoids introducing external resources, relying instead on perturbations to the input. Our training approach randomly masks certain tokens within the chain of thought, a technique we found to be particularly effective for reasoning tasks.
  arXiv  Detail & Related papers  (2024-03-04T16:21:54Z)
• Precise Learning of Source Code Contextual Semantics via Hierarchical Dependence Structure and Graph Attention Networks [28.212889828892664]
  We propose a novel source code model embedded with hierarchical dependencies. We introduce the syntactic structural of the basic block, i.e., its corresponding AST, in source code model to provide sufficient information. The results show that our model reduces the scale of parameters by 50% and achieves 4% improvement on accuracy on program classification task.
  arXiv  Detail & Related papers  (2021-11-20T04:03:42Z)

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.