拆分大模型与小模型，让工具使用更准确可靠。
Factored Agents: Decoupling In-Context Learning and Memorization for Robust Tool Use
- 大模型负责规划和动态学习，小模型专注记忆工具格式
- 实测显示规划准确率提升，错误容错能力更强
- 适合需要稳定调用接口的复杂任务系统
本文提出一种新型分解式智能体架构，以克服传统单体智能体在代理型AI中的局限。该架构将智能体拆分为两个专用组件：(1) 大语言模型（LLM），作为高层规划者和上下文学习者，可利用用户提示中的动态信息；(2) 小型语言模型，用于记忆工具格式与输出。这种解耦有效缓解了单体设计中常见的接口字段错误、缺失及幻觉问题，以及动态环境下的规划不佳现象。实证评估表明，该分解架构显著提升了规划准确率与错误容错能力，并揭示了上下文学习与静态记忆之间的内在权衡。结果表明，分解式方法是构建更鲁棒、更适应性强的代理型AI系统的有前景路径。
原文摘要 · Abstract (English)
In this paper, we propose a novel factored agent architecture designed to overcome the limitations of traditional single-agent systems in agentic AI. Our approach decomposes the agent into two specialized components: (1) a large language model (LLM) that serves as a high level planner and in-context learner, which may use dynamically available information in user prompts, (2) a smaller language model which acts as a memorizer of tool format and output. This decoupling addresses prevalent issues in monolithic designs, including malformed, missing, and hallucinated API fields, as well as suboptimal planning in dynamic environments. Empirical evaluations demonstrate that our factored architecture significantly improves planning accuracy and error resilience, while elucidating the inherent trade-off between in-context learning and static memorization. These findings suggest that a factored approach is a promising pathway for developing more robust and adaptable agentic AI systems.
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。