SAGE: A Novelty Gate for Efficient Memory Evolution in Agentic LLMs 事件

SAGE: A Novelty Gate for Efficient Memory Evolution in Agentic LLMs arXiv:2605.30711v1 Announce Type: new Abstract: Agentic LLMs must continuously decide whether newly extracted facts should be added, merged with existing memories, or ignored, yet prior work has focused more on retrieval and storage than on principled write-side control. We frame memory evolution as a novelty-detection problem and propose SAGE, a Spherical Adaptive Gate for memory Evolution that scores candidate facts with a vo