AI RESEARCH
GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking
arXiv CS.AI
•
ArXi:2605.04449v1 Announce Type: cross Dialogue State Tracking (DST) requires precise extraction of structured information from multi-domain conversations, a task where Large Language Models (LLMs) struggle despite their impressive general capabilities. We present GEM (Graph-Enhanced Mixture-of-Experts), a novel framework that combines language models and graph-structured dialogue understanding with ReAct agent-based reasoning for superior DST performance.