Population-Evolve: a Parallel Sampling and Evolutionary Method for LLM Math Reasoning

📝 Original Info

• Title: Population-Evolve: a Parallel Sampling and Evolutionary Method for LLM Math Reasoning
• ArXiv ID: 2512.19081
• Date: 2025-12-22
• Authors: ** 논문에 명시된 저자 정보가 제공되지 않았습니다. (저자명 및 소속을 확인하려면 원문 PDF 혹은 arXiv 페이지를 참고하십시오.) **

📝 Abstract

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.

💡 Deep Analysis

📄 Full Content

Reference