.png){kind=icon}
Return
Optimizing multi-agent workflows via heterogeneous graph learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ipm.2026.105056.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Large Language Model (LLM)-based multi-agent systems (MAS) have shown promise for complex task solving, yet effective workflow design remains challenging due to poor scalability, limited use of historical context, and insufficient modeling of agent tool interactions in existing methods. To address these limitations, we propose Heterogeneous Graph-based workFlow optimization (HeGFlow), which models agents, tools, and the execution topology between agents and tools as interconnected graph components, transforming the design of MAS workflow into a heterogeneous graph adjacency matrix optimization problem. To efficiently explore the vast search space, HeGFlow introduces a two-stage matrix training process guided by a subgraph sampling strategy. Extensive experiments across six complex domains show that HeGFlow improves the average score of smaller LLM (e.g., Qwen3-8B) by 12.4%, enabling it to match or even surpass the performance of much larger models. Furthermore, HeGFlow achieves the best average performance of 79.7 on four widely-used benchmarks, which consistently outperforms existing manually design methods by an average of 3.7 similar to 7.8%, and surpasses the state-of-the-art automated workflow optimization methods by an average of 0.9 similar to 6.7%. Further experiments demonstrate that our graph-based approach achieves strong performance while maintaining low token consumption, establishing a new paradigm for scalable and effective MAS workflow generation. Code is available at https://anonymous.4open.science/r/Heterogeneous-graph_MAS-B28D/.
Keywords:
Multi-agent system
Heterogeneous graph
Workflow optimization
Large language models
Graph matrix optimization
Journal
I
IF:
6.9
Papers:
576
Citations:
0
Organization
Cited Papers
No cited papers available