TonyBai

Aug 5, 2026 · Artificial Intelligence

Why Filesystem‑Based Memory Beats Expectations for LLM Agents – 5 Surprising Findings

A new multi‑institution study formalizes LLM‑agent memory as a three‑role filesystem store, evaluates six memory shapes across four dialogue and one skill benchmark, and reveals that structured organization halves retrieval cost but does not guarantee higher answer accuracy, with model personality and toolsets driving the shape of the memory store.