AI RESEARCH

HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues

arXiv CS.CL

ArXi:2604.06845v1 Announce Type: new Long-term memory is critical for dialogue systems that continuous, sustainable, and personalized interactions. However, existing methods rely on continuous summarization or OpenIE-based graph construction paired with fixed Top-\textit{k} retrieval, leading to limited adaptability across query categories and high computational overhead.