Ming Wu and Pengyuan Zhu release Agent Zero Memory
Agent Zero Memory released — points out the limits of existing memory systems that rely on a single organizing principle, and presents a long-term memory system that runs three structures in parallel: an episodic timeline that records change over time, an entity-event graph that links people and projects across sessions, and a document store that anchors facts to citations. After an intent gate and a source router, it runs 3 tool-using loops concurrently, each doing hybrid embedding + lexical search over one store; attaches a source, timestamp and evidence pointer to every learned item; and reads under a citation lock, so that answers can cite only evidence the reader actually opened
Why it matters
A strand that reorganizes agent long-term memory, which had relied on a single graph structure, into a triple structure of timeline, graph and documents, with provenance tracking and citation locks. In the authors' own reporting, it scores 95.60% on LongMemEval and 93.60% on LoCoMo, and they claim that across 8 language models, despite about a 30-fold difference in cost per query, accuracy varies by only 3.4 percentage points — so what separates performance is not the choice of model but the memory architecture.
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2608.29606Added in Week 36, 2026 · See that week