From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction

ArXi:2604.27906v1 Announce Type: new Persistent AI memory is often reduced to a retrieval problem: prior interactions as text, embed them, and ask the model to recover relevant context later. This design is useful for thematic recall, but it is mismatched to the kinds of memory that agents need in production: exact facts, current state, updates and deletions, aggregation, relations, negative queries, and explicit unknowns. These operations require memory to behave less like search and like a system of record. This paper argues that reliable external AI memory must be schema-grounded.