让大模型智能体像人一样从经验中持续进化
FLEX: Continuous Agent Evolution via Forward Learning from Experience
- 通过持续反思成功失败构建结构化经验库，实现无梯度进化
- 在数学推理、化学逆合成等任务上提升最高达23%
- 发现经验可跨智能体继承，迈向可扩展的持续进化
由大语言模型驱动的自主智能体虽已革新推理与问题解决能力，但训练后即固化，无法在部署中随经验成长。本文提出前向经验学习（FLEX），一种无梯度学习范式，使LLM智能体可通过累积经验持续演化。FLEX通过持续反思与环境交互中的成败，构建结构化经验库，实现可扩展且可继承的进化。实验显示，在数学推理（AIME25）上提升23%，化学逆合成（USPTO50k）提升10%，蛋白功能预测（ProteinGym）提升14%。进一步发现经验增长存在清晰缩放规律，且经验可在不同智能体间传承，标志着向可扩展、可继承的持续智能体演化迈出关键一步。
原文摘要 · Abstract (English)
Autonomous agents driven by Large Language Models (LLMs) have revolutionized reasoning and problem-solving but remain static after training, unable to grow with experience as intelligent beings do during deployment. We introduce Forward Learning with EXperience (FLEX), a gradient-free learning paradigm that enables LLM agents to continuously evolve through accumulated experience. Specifically, FLEX cultivates scalable and inheritable evolution by constructing a structured experience library through continual reflection on successes and failures during interaction with the environment. FLEX delivers substantial improvements on mathematical reasoning, chemical retrosynthesis, and protein fitness prediction (up to 23% on AIME25, 10% on USPTO50k, and 14% on ProteinGym). We further identify a clear scaling law of experiential growth and the phenomenon of experience inheritance across agents, marking a step toward scalable and inheritable continuous agent evolution. Project Page: https://flex-gensi-thuair.github.io.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。