CoTEvol: Self-Evolving Chain-of-Thoughts for Data Synthesis in Mathematical Reasoning

• URL: http://arxiv.org/abs/2604.14768v1
• Date: Thu, 16 Apr 2026 08:29:22 GMT
• Title: CoTEvol: Self-Evolving Chain-of-Thoughts for Data Synthesis in Mathematical Reasoning
• Abstract summary: We propose CoTEvol, a genetic evolutionary framework that casts Chain-of-Thought generation as a population-based search over reasoning trajectories.<n>Lightweight, task-aware fitness functions are designed to guide the evolutionary process toward accurate and diverse reasoning.<n> Empirically, CoTEvol improves correct-CoT synthesis success by over 30% and enhances structural diversity, with markedly improved efficiency.
• Score: 56.866286835885994
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large Language Models (LLMs) exhibit strong mathematical reasoning when trained on high-quality Chain-of-Thought (CoT) that articulates intermediate steps, yet costly CoT curation hinders further progress. While existing remedies such as distillation from stronger LLMs and self-synthesis based on test-time search alleviate this issue, they often suffer from diminishing returns or high computing overhead.In this work, we propose CoTEvol, a genetic evolutionary framework that casts CoT generation as a population-based search over reasoning trajectories.Candidate trajectories are iteratively evolved through reflective global crossover at the trajectory level and local mutation guided by uncertainty at the step level, enabling holistic recombination and fine-grained refinement. Lightweight, task-aware fitness functions are designed to guide the evolutionary process toward accurate and diverse reasoning. Empirically, CoTEvol improves correct-CoT synthesis success by over 30% and enhances structural diversity, with markedly improved efficiency. LLMs trained on these evolutionary CoT data achieve an average gain of 6.6% across eight math benchmarks, outperforming previous distillation and self-synthesis approaches. These results underscore the promise of evolutionary CoT synthesis as a scalable and effective method for mathematical reasoning tasks.

Related papers

• Unified Data Selection for LLM Reasoning [66.0118347918729]
  Training Large Language Models (LLMs) for complex, long-CoT reasoning is often bottlenecked by the need for massive high-quality reasoning data.<n>We propose High-Entropy Sum (HES), a training-free metric that quantifies reasoning quality by summing only the entropy of the top (e.g., 0.5%) highest-entropy tokens in each reasoning sample.
  arXiv  Detail & Related papers  (2026-05-21T12:21:41Z)
• CoT-Saliency: Unified Chain-of-Thought Reasoning for Heterogeneous Saliency Tasks [96.64597365827046]
  We present the first unified framework that jointly handles three operationally heterogeneous saliency tasks.<n>We introduce a Chain-of-Thought (CoT) reasoning process in a Vision-Language Model (VLM) to bridge task heterogeneity.<n>We show our model matches or outperforms specialized SOTA methods and strong closed-source VLMs across all tasks.
  arXiv  Detail & Related papers  (2025-11-01T04:37:01Z)
• CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning [63.44477226386808]
  Chain-of-thought (CoT) distillation from advanced large language models (LLMs) has proven effective in general reasoning tasks.<n>But it struggles in scientific domains where even advanced models often produce incorrect or superficial reasoning.<n>We propose CoT-Evo, an evolutionary CoT distillation framework to overcome this problem.
  arXiv  Detail & Related papers  (2025-10-15T05:29:56Z)
• Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs [51.29260537017623]
  Large Language Models (LLMs) are emerging as versatile foundation models for computational chemistry.<n>These models often lack round-trip consistency.<n>We introduce Round-Trip Reinforcement Learning (RTRL), a novel framework that trains a model to improve its consistency.
  arXiv  Detail & Related papers  (2025-10-01T23:58:58Z)
• Compressing Chain-of-Thought in LLMs via Step Entropy [12.576398947428988]
  Large Language Models (LLMs) using Chain-of-Thought (CoT) prompting excel at complex reasoning but generate thought processes with considerable redundancy, leading to increased inference costs and reduced efficiency.<n>We introduce a novel CoT compression framework based on step entropy, a metric that quantifies the informational contribution of individual reasoning steps to identify redundancy.
  arXiv  Detail & Related papers  (2025-08-05T11:48:18Z)
• Mind the Gap: Bridging Thought Leap for Improved Chain-of-Thought Tuning [54.65050470296886]
  We propose the CoT Thought Leap Bridge Task, which aims to automatically detect leaps and generate missing intermediate reasoning steps.<n>We demonstrate that models fine-tuned on bridged datasets consistently outperform those trained on original datasets.<n>Our approach effectively enhances distilled data and provides better starting points for reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-20T17:59:31Z)
• Deconstructing Long Chain-of-Thought: A Structured Reasoning Optimization Framework for Long CoT Distillation [22.875285119636235]
  R1 distillation scheme has emerged as a promising approach for training cost-effective models with enhanced reasoning abilities.<n>This study examines the universality of distillation data and identifies key components that enable the efficient transfer of long-chain reasoning capabilities.<n>We propose DLCoT (Deconstructing Long Chain-of-Thought), a distillation data enhancement framework.
  arXiv  Detail & Related papers  (2025-03-20T17:46:38Z)

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.