将成功任务方案存为可执行代码，自动积累优化智能体能力。
AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse
- 把成功任务转化为可运行的子智能体代码，而非仅记录文字经验。
- 通过执行反馈持续优化子智能体，任务执行效率随使用提升。
- 代码可移植、免干预，适合需要长期进化能力的自动化系统。
构建基于大模型的智能体日益重要。现有自进化方法主要将成功经验以文本提示或反思形式记录，难以在复杂场景中保证任务高效重执行。我们提出 AgentFactory，一种新自进化范式：将成功任务解决方案保存为可执行的子智能体代码，而非文本经验。关键在于，这些子智能体基于执行反馈持续优化，随着任务增多变得越来越稳健和高效。保存的子智能体为标准 Python 代码，附带规范文档，可在任何支持 Python 的系统中复用。实验表明，AgentFactory 实现了能力的持续积累：其可执行子智能体库随时间增长并改进，显著降低相似任务的处理成本，且无需人工干预。实现已开源于 https://github.com/zzatpku/AgentFactory，演示视频见 https://youtu.be/iKSsuAXJHW0。
原文摘要 · Abstract (English)
Building LLM-based agents has become increasingly important. Recent works on LLM-based agent self-evolution primarily record successful experiences as textual prompts or reflections, which cannot reliably guarantee efficient task re-execution in complex scenarios. We propose AgentFactory, a new self-evolution paradigm that preserves successful task solutions as executable subagent code rather than textual experience. Crucially, these subagents are continuously refined based on execution feedback, becoming increasingly robust and efficient as more tasks are encountered. Saved subagents are pure Python code with standardized documentation, enabling portability across any Python-capable system. We demonstrate that AgentFactory enables continuous capability accumulation: its library of executable subagents grows and improves over time, progressively reducing the effort required for similar tasks without manual intervention. Our implementation is open-sourced at https://github.com/zzatpku/AgentFactory, and our demonstration video is available at https://youtu.be/iKSsuAXJHW0.
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。