作者位次 #3/8ACL 2026Poster· Natural Language Processing
H yper M em: Hypergraph Memory for Long-Term Conversations
Juwei Yue · Chuanrui Hu · Jiawei Sheng · Zuyi Zhou · Wenyuan Zhang · Tingwen Liu · Li Guo · Yafeng Deng
摘要
Long-term memory is essential for conversational agents to maintain coherence, track persistent tasks, and provide personalized interactions across extended dialogues. However, existing approaches as Retrieval-Augmented Generation (RAG) and graph-based memory mostly rely on pairwise relations, wh...