---
title: "Intent Hub: A Self-Healing Semantic Agent Routing System for Resolving Overlap in Agentic Systems"
authors:
  - "Chenrui Liang"
  - "Peng Xu"
  - "Xinyuan Liu"
doi: "10.24963/ijcai.2026/976"
url: "https://ijcai.org/proceedings/2026/976"
pdf: "https://ijcai.org/proceedings/2026/0976.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "8445-8448"
track: "Demo Track"
keywords:
  - "AI: Natural Language Processing"
  - "AI: Humans and AI"
  - "AI: Agent-based and Multi-agent Systems"
---

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

Chenrui Liang, Peng Xu, Xinyuan Liu

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 8445-8448. DOI: [10.24963/ijcai.2026/976](https://doi.org/10.24963/ijcai.2026/976)

## 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.