用认知模型和AI算法设计多LLM协作系统
Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents
- 提出代理模板框架，明确各LLM角色与组合方式
- 梳理文献中现有语言代理，发现其源于认知模型或AI算法
- 适合想提升代理可解释性与效率的研究者
尽管当前大语言模型（LLMs）在独立任务上能力日益增强，但仍有许多复杂问题超出单一模型的能力范围。对于此类任务，如何将多个LLM作为组件协同构建整体系统仍存在不确定性。本文认为，现有认知模型与人工智能（AI）算法文献中蕴含着设计模块化语言代理的潜在蓝图。为此，我们形式化提出一种代理模板概念，明确个体LLM的角色及其功能组合方式。随后，我们综述了文献中多种现有语言代理，并指出其底层设计直接源自认知模型或AI算法。通过揭示这些设计，我们旨在强调受认知科学与AI启发的代理模板，是开发高效、可解释语言代理的强大工具。
原文摘要 · Abstract (English)
While contemporary large language models (LLMs) are increasingly capable in isolation, there are still many difficult problems that lie beyond the abilities of a single LLM. For such tasks, there is still uncertainty about how best to take many LLMs as parts and combine them into a greater whole. This position paper argues that potential blueprints for designing such modular language agents can be found in the existing literature on cognitive models and artificial intelligence (AI) algorithms. To make this point clear, we formalize the idea of an agent template that specifies roles for individual LLMs and how their functionalities should be composed. We then survey a variety of existing language agents in the literature and highlight their underlying templates derived directly from cognitive models or AI algorithms. By highlighting these designs, we aim to call attention to agent templates inspired by cognitive science and AI as a powerful tool for developing effective, interpretable language agents.
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。