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

TL;DR

CoTEvol introduces a genetic evolutionary framework for generating diverse and accurate Chain-of-Thought reasoning trajectories, significantly improving mathematical reasoning performance in large language models.

Contribution

It presents a novel evolutionary approach to synthesize Chain-of-Thought data, outperforming existing methods in efficiency and reasoning accuracy.

Findings

Improves correct-CoT synthesis success by over 30%.

Enhances structural diversity of reasoning trajectories.

LLMs trained on CoTEvol data gain 6.6% on average across benchmarks.

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.