TensorX
返回文献探索

Paper · arXiv 2501.09891

Evolving Deeper LLM Thinking

Kuang-Huei Lee, Ian Fischer, Yueh-Hua Wu, Dave Marwood, Shumeet Baluja, Dale Schuurmans, Xinyun Chen

116 upvotesJanuary 17, 2025arXiv 预印本
AI 摘要

Mind Evolution, an evolutionary search strategy using a language model, outperforms other inference methods in natural language planning tasks by generating, recombining, and refining candidate responses.

evolutionary search strategyLarge Language ModelsMind Evolutionlanguage modelsolution evaluatorBest-of-NSequential Revisionnatural language planning tasksTravelPlannerNatural Plan benchmarksGemini 1.5 Pro

Abstract

We explore an evolutionary search strategy for scaling inference time compute in Large Language Models. The proposed approach, Mind Evolution, uses a language model to generate, recombine and refine candidate responses. The proposed approach avoids the need to formalize the underlying inference problem whenever a solution evaluator is available. Controlling for inference cost, we find that Mind Evolution significantly outperforms other inference strategies such as Best-of-N and Sequential Revision in natural language planning tasks. In the TravelPlanner and Natural Plan benchmarks, Mind Evolution solves more than 98% of the problem instances using Gemini 1.5 Pro without the use of a formal solver.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号
Evolving Deeper LLM Thinking | TensorX