SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligence

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yao, Lin, Chenyang, Tang, Shijie, Chen, Haokun, Zhou, Shijie, Ma, Yunpu, Tresp, Volker
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915350221684736
author Zhang, Yao
Lin, Chenyang
Tang, Shijie
Chen, Haokun
Zhou, Shijie
Ma, Yunpu
Tresp, Volker
author_facet Zhang, Yao
Lin, Chenyang
Tang, Shijie
Chen, Haokun
Zhou, Shijie
Ma, Yunpu
Tresp, Volker
contents 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15672
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligence
Zhang, Yao
Lin, Chenyang
Tang, Shijie
Chen, Haokun
Zhou, Shijie
Ma, Yunpu
Tresp, Volker
Artificial Intelligence
Multiagent Systems
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/.
title SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligence
topic Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2506.15672