Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations

ArXi:2602.19320v2 Announce Type: replace Agentic memory systems enable large language model (LLM) agents to maintain state across long interactions, ing long-horizon reasoning and personalization beyond fixed context windows. Despite rapid architectural development, the empirical foundations of these systems remain fragile: existing benchmarks are often underscaled, evaluation metrics are misaligned with semantic utility, performance varies significantly across backbone models, and system-level costs are frequently overlooked.