AgentSquare:模块化设计空间中的自动LLM智能体搜索
AgentSquare: Automatic LLM Agent Search in Modular Design Space
AI总结:
针对LLM智能体设计依赖手工且适应性差的问题,提出模块化设计空间与AgentSquare搜索框架,通过模块进化与重组机制自动搜索优化智能体,在六个基准上平均性能提升17.2%。
摘要:
近年来,大型语言模型(LLM)的进步推动了能够处理广泛复杂任务的智能体系统的快速发展。然而,当前研究在很大程度上依赖于手工的、特定于任务的设计,这限制了它们对新任务的适应性。在本文中,我们引入了一个新的研究问题:模块化LLM智能体搜索(MoLAS)。我们提出了一个模块化设计空间,将现有的LLM智能体设计抽象为四个具有统一IO接口的基本模块:规划(Planning)、推理(Reasoning)、工具使用(Tool Use)和记忆(Memory)。基于这一设计空间,我们提出了一种新颖的LLM智能体搜索框架,称为AgentSquare,它引入了两种核心机制,即模块进化和重组,以高效地搜索优化的LLM智能体。为了进一步加速这一过程,我们设计了一个性能预测器,它使用上下文代理模型来跳过没有前景的智能体设计。在涵盖网络、具身、工具使用和游戏应用的多样化场景的六个基准上的广泛实验表明,AgentSquare显著优于手工制作的智能体,与最知名的人工设计相比,平均性能提升了17.2%。此外,AgentSquare可以生成可解释的设计见解,从而更深入地理解智能体架构及其对任务性能的影响。我们相信,模块化设计空间和AgentSquare搜索框架为充分利用先前成功设计的潜力并整合研究社区的集体努力提供了一个平台。代码仓库可在https://github.com/tsinghua-fib-lab/AgentSquare获取。
英文摘要:
Recent advancements in Large Language Models (LLMs) have led to a rapid growth of agentic systems capable of handling a wide range of complex tasks. However, current research largely relies on manual, task-specific design, limiting their adaptability to novel tasks. In this paper, we introduce a new research problem: Modularized LLM Agent Search (MoLAS). We propose a modular design space that abstracts existing LLM agent designs into four fundamental modules with uniform IO interface: Planning, Reasoning, Tool Use, and Memory. Building on this design space, we present a novel LLM agent search framework called AgentSquare, which introduces two core mechanisms, i.e., module evolution and recombination, to efficiently search for optimized LLM agents. To further accelerate the process, we design a performance predictor that uses in-context surrogate models to skip unpromising agent designs. Extensive experiments across six benchmarks, covering the diverse scenarios of web, embodied, tool use and game applications, show that AgentSquare substantially outperforms hand-crafted agents, achieving an average performance gain of 17.2% against best-known human designs. Moreover, AgentSquare can generate interpretable design insights, enabling a deeper understanding of agentic architecture and its impact on task performance. We believe that the modular design space and AgentSquare search framework offer a platform for fully exploiting the potential of prior successful designs and consolidating the collective efforts of research community. Code repo is available at https://github.com/tsinghua-fib-lab/AgentSquare.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。