SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligence

TL;DR

SwarmAgentic introduces a fully automated framework for generating and optimizing agentic systems from scratch using swarm intelligence, significantly improving performance on complex, open-ended tasks.

Contribution

It presents a novel, fully automated system generation method combining swarm intelligence with language-driven exploration for scalable agentic system design.

Findings

Achieved +261.8% improvement over ADAS on TravelPlanner benchmark.

Successfully generated agentic systems from scratch for complex tasks.

Demonstrated effective joint optimization of agent functionality and collaboration.

Abstract

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/.