Population-Evolve: a Parallel Sampling and Evolutionary Method for LLM Math Reasoning
Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院);University of Chinese Academy of Sciences(中国科学院大学);Zhongguancun Academy(中关村学院);Zhongguancun Institute of Artificial Intelligence(中关村人工智能研究院)
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.
Mem$^2$Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation
Beihang University(北京航空航天大学);Beijing Institute of Technology(北京理工大学);Independent Researcher(独立研究者);Munich Center for Machine Learning(慕尼黑机器学习中心);University of Edinburgh(爱丁堡大学)
EvolVE: Evolutionary Search for LLM-based Verilog Generation and Optimization
Department of Electrical Engineering(电气工程系);National Taiwan University(国立台湾大学);Department of Computer Science and Information Engineering(计算机科学与信息工程系);Institute of Information Science(信息科学研究所)
Autonomous Algorithm Discovery for Ptychography via Evolutionary LLM Reasoning
Advanced Photon Source, Argonne National Laboratory, Lemont, IL, USA(阿贡国家实验室先进光子源);Department of Materials Science and NanoEngineering, Rice University, Houston, TX, USA(材料科学与纳米工程系,德克萨斯大学里士满分校)
MolEvolve: LLM-Guided Evolutionary Search for Interpretable Molecular Optimization
Hong Kong University of Science(香港科技大学);Hong Kong Polytechnic University(香港理工大学);Tsinghua University(清华大学);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳))
Reactive, Proactive, and Inductive Agents: An evolutionary path for biological and artificial spiking networks
Sony Computer Science Laboratories, Inc.(索尼计算机科学研究所);Earth-Life Science Institute, Tokyo Institute of Technology(东京工业大学地球生命研究所);The University of Tokyo(东京大学)
Zuse Institute Berlin(柏林Zuse研究所);Technical University of Berlin(柏林技术大学);Hong Kong Baptist University(香港 Baptist大学);RIKEN Center for Advanced Intelligence Project(RIKEN高级智能项目中心)
Robots Need Some Education: On the complexity of learning in evolutionary robotics
University of Oslo(奥斯陆大学);École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院);Leiden University(莱顿大学);Edinburgh Napier University(爱丁堡龙比亚大学);Vrije Universiteit Amsterdam(阿姆斯特丹自由大学)