BriefGPT.xyz
Jan, 2024
小型LLM是弱工具学习者:多LLM代理
Small LLMs Are Weak Tool Learners: A Multi-LLM Agent
HTML
PDF
Weizhou Shen, Chenliang Li, Hongzhan Chen, Ming Yan, Xiaojun Quan...
TL;DR
我们提出了一个模块化的多语言模型框架,将大型语言模型能力分解为规划器、调用器和摘要生成器,并通过两阶段训练范式有效地训练该框架,该框架在各种工具使用基准测试中表现出超越传统单语言模型方法的效果,凸显了其在工具学习中的功效和优势。
Abstract
large language model
(LLM) agents significantly extend the capabilities of standalone LLMs, empowering them to interact with external tools (e.g., APIs, functions) and complete complex tasks in a self-directed fashion. The challenge of
→