MixReasoning: Switching Modes to Think

• URL: http://arxiv.org/abs/2510.06052v1
• Date: Tue, 07 Oct 2025 15:46:34 GMT
• Title: MixReasoning: Switching Modes to Think
• Authors: Haiquan Lu, Gongfan Fang, Xinyin Ma, Qi Li, Xinchao Wang,
• Abstract summary: Reasoning models enhance performance by tackling problems in a step-by-step manner.<n>Applying extended reasoning to every step introduces substantial redundancy.<n>We propose MixReasoning, a framework that dynamically adjusts the depth of reasoning within a single response.
• Score: 79.70845484191543
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of thought before producing an answer. However, applying extended reasoning to every step introduces substantial redundancy, as sub-problems vary widely in difficulty and complexity: a small number of pivotal steps are genuinely challenging and decisive for the final answer, while many others only involve straightforward revisions or simple computations. Therefore, a natural idea is to endow reasoning models with the ability to adaptively respond to this variation, rather than treating all steps with the same level of elaboration. To this end, we propose MixReasoning, a framework that dynamically adjusts the depth of reasoning within a single response. The resulting chain of thought then becomes a mixture of detailed reasoning on difficult steps and concise inference on simpler ones. Experiments on GSM8K, MATH-500, and AIME show that MixReasoning shortens reasoning length and substantially improves efficiency without compromising accuracy.

Related papers

• 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)
• Think Smart, Not Hard: Difficulty Adaptive Reasoning for Large Audio Language Models [28.578488403845146]
  Large Audio Language Models (LALMs) have shown remarkable reasoning capabilities.<n>We propose a difficulty-adaptive reasoning method for LALMs.
  arXiv  Detail & Related papers  (2025-09-26T06:49:14Z)
• Less is More Tokens: Efficient Math Reasoning via Difficulty-Aware Chain-of-Thought Distillation [82.2288581878096]
  We present a framework for difficulty-aware reasoning that teaches models to dynamically adjust reasoning depth based on problem complexity.<n>We show that models can be endowed with such dynamic inference pathways without any architectural modifications.
  arXiv  Detail & Related papers  (2025-09-05T16:40:13Z)
• Are Retrials All You Need? Enhancing Large Language Model Reasoning Without Verbalized Feedback [2.2406151150434894]
  We introduce the concept of retrials without feedback''<n>Unlike conventional iterative refinement methods, our method does not require explicit self-reflection or verbalized feedback.<n>Our findings indicate that simpler retrial-based approaches often outperform more sophisticated reasoning frameworks.
  arXiv  Detail & Related papers  (2025-04-17T13:52:48Z)
• DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models [30.184895117009457]
  This paper introduces Difficulty-Adaptive Slow Thinking (DAST), a novel framework that enables models to autonomously adjust the length of Chain-of-Thought (CoT) based on problem difficulty.<n>Experiments on diverse datasets and model scales demonstrate that DAST effectively mitigates overthinking while preserving reasoning accuracy on complex problems.
  arXiv  Detail & Related papers  (2025-03-06T14:23:06Z)
• Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models [56.37421741507468]
  Chain-of-Thought (CoT) reasoning has significantly enhanced the performance of large language models (LLMs)<n>We propose a method to identify critical reasoning steps using perplexity as a measure of their importance.
  arXiv  Detail & Related papers  (2025-02-18T20:04:51Z)
• Distilling Reasoning Ability from Large Language Models with Adaptive Thinking [54.047761094420174]
  Chain of thought finetuning (cot-finetuning) aims to endow small language models (SLM) with reasoning ability to improve their performance towards specific tasks.<n>Most existing cot-finetuning methods adopt a pre-thinking mechanism, allowing the SLM to generate a rationale before providing an answer.<n>This mechanism enables SLM to analyze and think about complex questions, but it also makes answer correctness highly sensitive to minor errors in rationale.<n>We propose a robust post-thinking mechanism to generate answers before rationale.
  arXiv  Detail & Related papers  (2024-04-14T07:19:27Z)
• Faith and Fate: Limits of Transformers on Compositionality [109.79516190693415]
  We investigate the limits of transformer large language models across three representative compositional tasks. These tasks require breaking problems down into sub-steps and synthesizing these steps into a precise answer. Our empirical findings suggest that transformer LLMs solve compositional tasks by reducing multi-step compositional reasoning into linearized subgraph matching.
  arXiv  Detail & Related papers  (2023-05-29T23:24:14Z)

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.