Population-Evolve: a Parallel Sampling and Evolutionary Method for LLM Math Reasoning
By: Yanzhi Zhang , Yitong Duan , Zhaoxi Zhang and more
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.
Similar Papers
Nature-Inspired Population-Based Evolution of Large Language Models
Computation and Language
Makes AI learn new things much faster.
Evolutionary thoughts: integration of large language models and evolutionary algorithms
Neural and Evolutionary Computing
AI learns faster by trying many ideas.
Evolving Deeper LLM Thinking
Artificial Intelligence
Teaches computers to plan trips better and faster.