一作ACL 2026Poster· Natural Language Processing
GAM : Hierarchical Graph-based Agentic Memory for LLM Agents
Zhaofen Wu · Hanrong Zhang · Fulin Lin · Wujiang Xu · Xinran Xu · Yankai Chen · Henry Peng Zou · shaowen chen · Weizhi Zhang · Xue Liu · Philip S. Yu · Hongwei Wang
摘要
To sustain coherent long-term interactions, Large Language Model (LLM) agents must navigate the tension between acquiring new information and retaining prior knowledge. Current unified stream-based memory systems facilitate context updates but remain vulnerable to interference from transient nois...