Baofeng Zhao

Salience, Ranking, and Metabolism: Three Conflated Signals in Long-Running Agent Memory Systems

Long-running agent memory systems commonly treat "importance" as a single quantity. We argue that it conflates three distinct signals, and that the conflation is a structural design error rather than an implementation detail. A scoring formula written in 2023 for a simulation dem...

Cold-Start Ranking: Architectural Semantic Labels Predict Memory Use Where Graph Methods Go Blind

In agent memory systems, graph-based ranking methods go blind at cold-start: 91% of new nodes remain invisible to PageRank and access-count scores throughout the observation window. Architectural semantic labels assigned at node creation predict future organic use at AUC 0.84, a...

Cold-Start Ranking: Architectural Semantic Labels Predict Memory Use Where Graph Methods Go Blind

In agent memory systems, graph-based ranking methods go blind at cold-start: 91% of new nodes remain invisible to PageRank and access-count scores throughout the observation window. Architectural semantic labels assigned at node creation predict future organic use at AUC 0.84, a...