让AI代理自动进化，应对无限场景任务。
InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarios
- 构建金字塔式多代理框架，自动拆解复杂任务
- 比同类框架性能高9.9%，支持并行执行提升效率
- 适合需要持续优化的智能助手与自动化系统
大型语言模型代理在组织和执行复杂任务方面展现出强大能力，但其开发依赖精心设计的工作流、提示词及迭代调优，需具备模型技术和领域专长，限制了跨行业规模化与成本效益。为此，我们提出InfiAgent——一种基于有向无环图的金字塔式多代理框架，可适用于无限场景。该框架引入四项关键创新：通用的“代理即工具”机制，实现复杂代理的层级化自动分解；双审计机制保障任务完成质量与稳定性；代理路由功能实现高效任务-代理匹配；以及代理自演化机制，可根据新任务、表现不佳或优化机会自主重构代理图结构。此外，原子级任务设计支持代理并行，显著提升执行效率。评估结果表明，InfiAgent在多个基准上比ADAS（同类自动生成代理框架）性能高出9.9%。案例研究显示，其生成的科学论文已获顶级IEEE会议人类评审认可。
原文摘要 · Abstract (English)
Large Language Model (LLM) agents have demonstrated remarkable capabilities in organizing and executing complex tasks, and many such agents are now widely used in various application scenarios. However, developing these agents requires carefully designed workflows, carefully crafted prompts, and iterative tuning, which requires LLM techniques and domain-specific expertise. These hand-crafted limitations hinder the scalability and cost-effectiveness of LLM agents across a wide range of industries. To address these challenges, we propose \textbf{InfiAgent}, a Pyramid-like DAG-based Multi-Agent Framework that can be applied to \textbf{infi}nite scenarios, which introduces several key innovations: a generalized "agent-as-a-tool" mechanism that automatically decomposes complex agents into hierarchical multi-agent systems; a dual-audit mechanism that ensures the quality and stability of task completion; an agent routing function that enables efficient task-agent matching; and an agent self-evolution mechanism that autonomously restructures the agent DAG based on new tasks, poor performance, or optimization opportunities. Furthermore, InfiAgent's atomic task design supports agent parallelism, significantly improving execution efficiency. This framework evolves into a versatile pyramid-like multi-agent system capable of solving a wide range of problems. Evaluations on multiple benchmarks demonstrate that InfiAgent achieves 9.9\% higher performance compared to ADAS (similar auto-generated agent framework), while a case study of the AI research assistant InfiHelper shows that it generates scientific papers that have received recognition from human reviewers at top-tier IEEE conferences.
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。