Augmented Runtime Collaboration for Self-Organizing Multi-Agent Systems: A Hybrid Bi-Criteria Routing Approach
Qingwen Yang, Feiyu Qu, Tiezheng Guo, Yanyi Liu, Yingyou Wen
Abstract
LLM-based multi-agent systems have demonstrated significant capabilities across diverse domains. However, the task performance and efficiency are fundamentally constrained by their collaboration strategies. Prevailing approaches rely on static topologies and centralized global planning, a paradigm that limits their scalability and adaptability in open, decentralized networks. Effective collaboration planning in distributed systems using only local information thus remains a formidable challenge. To address this, we propose BiRouter, a novel dual-criteria routing method for Self-Organizing Multi-Agent Systems (SO-MAS). This method enables each agent to autonomously execute "next-hop" task routing at runtime, relying solely on local information. Its core decision-making mechanism is predicated on balancing two metrics: (1) the ImpScore, which evaluates a candidate agent
BibTeX
@inproceedings{aaai2026_augmentedruntime,
title = {Augmented Runtime Collaboration for Self-Organizing Multi-Agent Systems: A Hybrid Bi-Criteria Routing Approach},
author = {Qingwen Yang and Feiyu Qu and Tiezheng Guo and Yanyi Liu and Yingyou Wen},
booktitle = {AAAI 2026},
year = {2026}
}