让大模型从用工具变成自己设计自动化流程
Synthesizing Procedural Memory: Challenges and Architectures in Automated Workflow Generation
- 用假设-探测-编码的科学方法自动生成可执行流程
- 解决四大瓶颈，生成能直接投入生产的代码技能
- 适合做自动化系统开发的研究者和工程师
尽管CodeMem已确立可执行代码是智能体程序记忆的最佳表示，但从零开始自主合成这种记忆的机制仍鲜有研究。本文推动大语言模型从被动工具使用者转变为主动工作流架构师。通过一个涉及Outlook与OneDrive跨服务编排的高保真案例研究，我们识别并解决了自动化技能生成中的四个结构性瓶颈：发现差距（导航大型工具注册表）、验证差距（确定工具响应结构）、分解差距（以线性状态锚定替代低效搜索）以及扩展差距（关注并发与持久性）。实验表明，通过强制执行假设、探测、编码的科学方法，智能体能够自主生成稳健且可投入生产的代码技能。
原文摘要 · Abstract (English)
While CodeMem establishes executable code as the optimal representation for agentic procedural memory, the mechanism for autonomously synthesizing this memory from a blank slate remains underexplored. This paper operationalizes the transition of Large Language Models from passive tool-users to active workflow architects. Through a high-fidelity case study of a cross-service orchestration task involving Outlook and OneDrive, we identify and address four structural bottlenecks in automated skill generation: the Discovery Gap involving navigation of large tool registries, the Verification Gap regarding grounding tool response structures, the Decomposition Gap which replaces inefficient search with Linear State Anchoring, and the Scaling Gap focused on concurrency and persistence. We demonstrate that by enforcing a scientific methodology of hypothesize, probe, and code, agents can autonomously write robust, production-grade code skills.
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。