Self-Organizing Agent Network for LLM-based Workflow Automation

TL;DR

This paper introduces SOAN, a novel framework that improves LLM-based workflow automation by building modular, formalized agent networks to handle complex, nested enterprise workflows more effectively.

Contribution

The paper presents SOAN, a structure-driven orchestration framework that incrementally constructs agent networks for better handling of complex, multi-layered workflows in enterprise environments.

Findings

SOAN outperforms existing methods in adaptability and fault tolerance.

SOAN achieves higher execution efficiency in complex workflows.

Experimental results validate SOAN's effectiveness on benchmarks and real-world data.

Abstract

Recent multi-agent frameworks built upon large language models (LLMs) have demonstrated remarkable capabilities in complex task planning. However, in real-world enterprise environments, business workflows are typically composed through modularization and reuse of numerous subprocesses, resulting in intricate workflows characterized by lengthy and deeply nested execution paths. Such complexity poses significant challenges for LLM-driven orchestration, as extended reasoning chains and state-space explosions severely impact planning effectiveness and the proper sequencing of tool invocations. Therefore, developing an orchestration method with controllable structures capable of handling multi-layer nesting becomes a critical issue. To address this, we propose a novel structure-driven orchestration framework Self-Organizing Agent Network (SOAN). SOAN incrementally builds a formalized agent network by identifying and encapsulating structural units as independent agents, enhancing modularity and clarity in orchestration. Extensive evaluations were performed using multiple benchmarks as well as a real-world enterprise workflow dataset. Experimental results demonstrate that SOAN significantly outperforms state-of-the-art methods in terms of adaptability, fault tolerance, and execution efficiency.