用进化算法提升大模型数学推理能力，无需训练即可优化答案
Population-Evolve: a Parallel Sampling and Evolutionary Method for LLM Math Reasoning
- 维护多个候选答案并行演化，通过自洽提示不断优化
- 在MATH、GSM8K等数据集上准确率超越现有方法，方差更小
- 适合追求高精度推理且不希望额外训练的用户
测试时扩展已成为近年提升大语言模型推理能力的有前景方向。本文提出Population-Evolve，一种受遗传算法启发的无训练方法，用于优化大模型推理。该方法通过并行推理维持每个问题的动态候选解群体，并引入演化提示，使大模型在每轮迭代中自我优化群体。收敛后，通过多数投票确定最终答案。此外，我们构建了一个统一框架，从遗传算法视角解释现有测试时扩展策略。实验表明，Population-Evolve在保持低性能方差和计算效率的同时，实现更优的准确率。研究结果凸显了演化策略在推理阶段释放大模型推理潜力的巨大潜力。
原文摘要 · Abstract (English)
Test-time scaling has emerged as a promising direction for enhancing the reasoning capabilities of Large Language Models in last few years. In this work, we propose Population-Evolve, a training-free method inspired by Genetic Algorithms to optimize LLM reasoning. Our approach maintains a dynamic population of candidate solutions for each problem via parallel reasoning. By incorporating an evolve prompt, the LLM self-evolves its population in all iterations. Upon convergence, the final answer is derived via majority voting. Furthermore, we establish a unification framework that interprets existing test-time scaling strategies through the lens of genetic algorithms. Empirical results demonstrate that Population-Evolve achieves superior accuracy with low performance variance and computational efficiency. Our findings highlight the potential of evolutionary strategies to unlock the reasoning power of LLMs during inference.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。