---
title: "MC-RAG System: A Structure-Driven RAG System for Multi-Constraint Queries"
authors:
  - "Xiao Zhang"
  - "Yang Wan"
  - "Yi Li"
  - "Miao Xie"
  - "Chunli Lv"
doi: "10.24963/ijcai.2026/1002"
url: "https://ijcai.org/proceedings/2026/1002"
pdf: "https://ijcai.org/proceedings/2026/1002.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "8555-8559"
track: "Demo Track"
keywords:
  - "AI: Natural Language Processing"
  - "AI: Knowledge Representation and Reasoning"
---

# MC-RAG System: A Structure-Driven RAG System for Multi-Constraint Queries

Xiao Zhang, Yang Wan, Yi Li, Miao Xie, Chunli Lv

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 8555-8559. DOI: [10.24963/ijcai.2026/1002](https://doi.org/10.24963/ijcai.2026/1002)

## Abstract

Retrieval-Augmented Generation (RAG) systems are widely adopted in question answering, yet they often fail to satisfy complex multi-constraint queries, leading to constraint violations, factual inconsistencies, or hallucinations. We present Structure-Driven RAG System for Multi-Constraint Queries(MC-RAG), a structure-driven RAG system that reformulates retrieval as a subgraph matching problem over a knowledge graph. By integrating semantic and structural embeddings with path-level indexing, MC-RAG performs interpretable, structure-aware, and constraint-consistent retrieval and generation. During the demonstration, participants can input medical or encyclopedic multi-constraint queries, visualize how the system parses constraints, performs structural matching, and generates answers, thereby experiencing an end-to-end, interactive, and explainable RAG pipeline. 
A demo video is available at https://youtu.be/J8kahzmAnu0.