Population-Evolve: a Parallel Sampling and Evolutionary Method for LLM Math Reasoning
This addresses the challenge of improving LLM reasoning capabilities during inference for applications in math and logic, representing an incremental advancement in test-time scaling methods.
The paper tackles the problem of enhancing Large Language Models' math reasoning by proposing Population-Evolve, a training-free method using genetic algorithms and parallel sampling, which achieves superior accuracy with low variance and computational efficiency.
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.