Computer Science
SGMEM: SENTENCE GRAPH MEMORY FOR LONG-TERM CONVERSATIONAL AGENTS
Y. Wu, Y. Zhang, et al.
SGMem (Sentence Graph Memory) represents dialogue as sentence-level graphs within chunked units, combining retrieved raw dialogue with generated memory like summaries, facts, and insights to supply LLMs with coherent, relevant context. Experiments on LongMemEval and LoCoMo show SGMem improves accuracy and outperforms strong baselines. Research conducted by Yaxiong Wu, Yongyue Zhang, Sheng Liang, and Yong Liu.
Related Publications
Explore these studies to deepen your understanding
Adjacent work that informs or extends this paper's methodology and findings.
Computer Science
Memory Management and Contextual Consistency for Long-Running Low-Code Agents
J. Xu
Psychology
Long-term memory guides resource allocation in working memory
A. L. Bruning and J. A. Lewis-peacock
Business
Financial time series prediction under Covid-19 pandemic crisis with Long Short-Term Memory (LSTM) network
M. Mroua and A. Lamine
Veterinary Science
Long-term molecular surveillance provides clues on a cattle origin for *Mycobacterium bovis* in Portugal
A. C. Reis, R. Tenreiro, et al.
