Proceedings

Automated Decision-Making on Networks with LLMs through Knowledge-Guided Evolution

Xiaohan Zheng, Lanning Wei, Yong Li, Quanming Yao

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Demo Track. Pages 11137-11140.

https://doi.org/10.24963/ijcai.2025/1279

Keywords

  • Machine Learning: ML: Deep learning architectures
  • Machine Learning: ML: Automated machine learning
  • Knowledge Representation and Reasoning: KRR: Applications
  • Agent-based and Multi-agent Systems: MAS: Applications

Abstract

Effective decision-making on networks often relies on learning from graph-structured data, where Graph Neural Networks (GNNs) play a central role, but they take efforts to configure and tune. In this demo, we propose LLMNet, showing how to design GNN automated through Large Language Models. Our system develops a set of agents that construct graph-related knowlege bases and then leverages Retrieval-Augmented Generation (RAG) to support automated configuration and refinement of GNN models through a knowledge-guided evolution process. These agents, equipped with specialized knowledge bases, extract insights into tasks and graph structures by interacting with the knowledge bases.Empirical results show LLMNet excels in twelve datasets across three graph learning tasks, validating its effectiveness of GNN model designing.

Xiaohan Zheng, Lanning Wei, Yong Li, and Quanming Yao. 2025. Automated Decision-Making on Networks with LLMs through Knowledge-Guided Evolution. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 11137–11140. https://doi.org/10.24963/ijcai.2025/1279
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards