AutoMaAS自动优化大模型多智能体架构，按任务复杂度动态分配资源。
AutoMaAS: Self-Evolving Multi-Agent Architecture Search for Large Language Models
- 通过性能-成本分析自动生成、合并或淘汰智能体组件。
- 实测在6个基准上提升1.0%-7.1%性能，推理成本降低3%-5%。
- 适合需要自适应资源调度的复杂多智能体系统研发者。
基于大语言模型的多智能体系统在多个领域展现出强大能力，但现有自动化设计方法通常采用单一整体方案，无法根据查询复杂度和领域需求动态调整资源分配。本文提出AutoMaAS，一种自演化多智能体架构搜索框架，借鉴神经架构搜索思想，通过动态操作符生命周期管理与自动化机器学习技术，自动发现最优智能体配置。该方法包含四项创新：(1) 基于性能-成本分析的自动操作符生成、融合与消除；(2) 实时参数调整的动态成本感知优化；(3) 在线反馈集成实现架构持续优化；(4) 通过决策追踪机制增强可解释性。在六个基准上的大量实验表明，与当前最优方法相比，AutoMaAS实现了1.0%-7.1%的性能提升，同时推理成本降低3%-5%。该框架在不同数据集和大语言模型主干上表现出优异的泛化能力，为大模型时代多智能体系统的自动化设计树立了新范式。
原文摘要 · Abstract (English)
Multi-agent systems powered by large language models have demonstrated remarkable capabilities across diverse domains, yet existing automated design approaches seek monolithic solutions that fail to adapt resource allocation based on query complexity and domain requirements. This paper introduces AutoMaAS, a self-evolving multi-agent architecture search framework that leverages neural architecture search principles to automatically discover optimal agent configurations through dynamic operator lifecycle management and automated machine learning techniques. Our approach incorporates four key innovations: (1) automatic operator generation, fusion, and elimination based on performance-cost analysis, (2) dynamic cost-aware optimization with real-time parameter adjustment, (3) online feedback integration for continuous architecture refinement, and (4) enhanced interpretability through decision tracing mechanisms. Extensive experiments across six benchmarks demonstrate that AutoMaAS achieves 1.0-7.1\% performance improvement while reducing inference costs by 3-5\% compared to state-of-the-art methods. The framework shows superior transferability across datasets and LLM backbones, establishing a new paradigm for automated multi-agent system design in the era of large language models.
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。