OFA-MAS: One-for-All Multi-Agent System Topology Design based on Mixture-of-Experts Graph Generative Models
Open Access
- 12 April 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1333-1344
Abstract
No abstract availableAll Related Versions
Funding Information
- Australian Research Council (ARC) (DP240101547)
- Australian Research Council (DE260101172)
This publication has 13 references indexed in Scilit:
- Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph GenerationProceedings of the AAAI Conference on Artificial Intelligence, 2026
- Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test TimeProceedings of the AAAI Conference on Artificial Intelligence, 2026
- A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models2025
- FreeGAD: A Training-Free yet Effective Approach for Graph Anomaly Detection2025
- A Label-free Heterophily-guided Approach for Unsupervised Graph Fraud DetectionProceedings of the AAAI Conference on Artificial Intelligence, 2025
- Noise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimation2024
- A survey on multi-agent reinforcement learning and its applicationJournal of Automation and Intelligence, 2024
- Graph of Thoughts: Solving Elaborate Problems with Large Language ModelsProceedings of the AAAI Conference on Artificial Intelligence, 2024
- A survey of multi-agent deep reinforcement learning with communicationAutonomous Agents and Multi-Agent Systems, 2024
- Are NLP Models really able to Solve Simple Math Word Problems?2021