IJCAI 20260 citations

Intent Hub: A Self-Healing Semantic Agent Routing System for Resolving Overlap in Agentic Systems

Chenrui Liang, Peng Xu, Xinyuan Liu

Abstract

Semantic overlap poses a fundamental challenge to accurate agent routing in large-scale agentic systems. We present Intent Hub, a self-healing semantic agent routing system that combines offline semantic diagnosis with an online Dual Filtering Mechanism. By leveraging LLM-generated augmentative positive and adversarial negative utterances, Intent Hub constructs explicit decision boundaries and enables interpretable, millisecond-level routing under high semantic overlap. Intent Hub further supports interactive semantic debugging, allowing developers to visually diagnose conflicts, repair routing rules, and immediately observe changes in online agent routing.

BibTeX
@inproceedings{ijcai2026_intenthubaselfhe,
  title = {Intent Hub: A Self-Healing Semantic Agent Routing System for Resolving Overlap in Agentic Systems},
  author = {Chenrui Liang and Peng Xu and Xinyuan Liu},
  booktitle = {IJCAI 2026},
  year = {2026}
}
Intent Hub: A Self-Healing Semantic Agent Routing System for Resolving Overlap in Agentic Systems · IJCAI 2026