AI RESEARCH
TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering
arXiv CS.CL
•
ArXi:2604.11193v1 Announce Type: new Multi-hop Knowledge Graph Question Answering (KGQA) requires coherent reasoning across relational paths, yet existing methods often treat each reasoning step independently and fail to effectively leverage experience from prior explorations, leading to fragmented reasoning and redundant exploration.