Intent Hub: A Self-Healing Semantic Agent Routing System for Resolving Overlap in Agentic Systems
Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Demo Track. Pages 8445-8448.
https://doi.org/10.24963/ijcai.2026/976
Keywords
- AI: Natural Language Processing
- AI: Humans and AI
- AI: Agent-based and Multi-agent Systems
Abstract
Semantic overlap challenges accurate agent routing in large-scale agentic systems. We present Intent Hub, a self-healing semantic agent routing system that combines offline asynchronous HITL repair with online Dual Filtering. LLM-generated positive and adversarial negative utterances help construct explicit decision boundaries, enabling interpretable millisecond-level routing. Intent Hub further supports interactive semantic debugging, allowing developers to diagnose conflicts, repair rules, and observe online routing changes.
@inproceedings{ijcai2026p976,
title = {Intent Hub: A Self-Healing Semantic Agent Routing System for Resolving Overlap in Agentic Systems},
author = {Liang, Chenrui and Xu, Peng and Liu, Xinyuan},
booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-26}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Diego Calvanese},
pages = {8445--8448},
year = {2026},
month = {8},
note = {Demo Track},
doi = {10.24963/ijcai.2026/976},
url = {https://doi.org/10.24963/ijcai.2026/976},
}
TY - CPAPER TI - Intent Hub: A Self-Healing Semantic Agent Routing System for Resolving Overlap in Agentic Systems AU - Liang, Chenrui AU - Xu, Peng AU - Liu, Xinyuan T2 - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26 PB - International Joint Conferences on Artificial Intelligence Organization PY - 2026 SP - 8445 EP - 8448 DO - 10.24963/ijcai.2026/976 UR - https://doi.org/10.24963/ijcai.2026/976 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
