SwarmAgentic：基于群体智能实现全自动化代理系统生成

SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligence

June 18, 2025

作者: Yao Zhang, Chenyang Lin, Shijie Tang, Haokun Chen, Shijie Zhou, Yunpu Ma, Volker Tresp

cs.AI

摘要

大型语言模型的快速发展推动了智能体系统在决策、协调和任务执行方面的进步。然而，现有的智能体系统生成框架缺乏完全自主性，缺失从零开始的智能体生成、自我优化的智能体功能以及协作能力，限制了系统的适应性和可扩展性。我们提出了SwarmAgentic，一个用于全自动化智能体系统生成的框架，该框架从零构建智能体系统，并通过语言驱动的探索联合优化智能体功能和协作作为相互依赖的组件。为了实现对系统级结构的高效搜索，SwarmAgentic维护一组候选系统，并通过反馈引导的更新进行演化，灵感来源于粒子群优化（PSO）。我们在六项涉及高级规划、系统级协调和创造性推理的真实世界、开放性和探索性任务上评估了我们的方法。仅给定任务描述和目标函数，SwarmAgentic在所有基准测试中均表现优异，在TravelPlanner基准上相对于ADAS实现了+261.8%的相对提升，凸显了全自动化在结构无约束任务中的有效性。该框架标志着向可扩展和自主智能体系统设计迈出了重要一步，将群体智能与全自动化系统多智能体生成相结合。我们的代码已公开发布于https://yaoz720.github.io/SwarmAgentic/。

English

The rapid progress of Large Language Models has advanced agentic systems in decision-making, coordination, and task execution. Yet, existing agentic system generation frameworks lack full autonomy, missing from-scratch agent generation, self-optimizing agent functionality, and collaboration, limiting adaptability and scalability. We propose SwarmAgentic, a framework for fully automated agentic system generation that constructs agentic systems from scratch and jointly optimizes agent functionality and collaboration as interdependent components through language-driven exploration. To enable efficient search over system-level structures, SwarmAgentic maintains a population of candidate systems and evolves them via feedback-guided updates, drawing inspiration from Particle Swarm Optimization (PSO). We evaluate our method on six real-world, open-ended, and exploratory tasks involving high-level planning, system-level coordination, and creative reasoning. Given only a task description and an objective function, SwarmAgentic outperforms all baselines, achieving a +261.8% relative improvement over ADAS on the TravelPlanner benchmark, highlighting the effectiveness of full automation in structurally unconstrained tasks. This framework marks a significant step toward scalable and autonomous agentic system design, bridging swarm intelligence with fully automated system multi-agent generation. Our code is publicly released at https://yaoz720.github.io/SwarmAgentic/.