MEMOREPAIR: Barrier-First Cascade Repair in Agentic Memory

TL;DR

MemoRepair introduces a barrier-first cascade repair method for agentic memory, effectively updating invalidated derived artifacts to maintain consistency and reduce stale information in memory systems.

Contribution

It formalizes the cascade update problem and provides an exact solution using max-weight predecessor closure via min-cut, improving memory repair efficiency.

Findings

Reduces invalidated-memory exposure from 69.8-94.3% to 0%.

Recovers over 91% of validated successors compared to exhaustive repair.

Cuts repair-operator cost by approximately 24-43%.

Abstract

Agentic memory evolves across tasks into durable derived artifacts: summaries, cached outputs, embeddings, learned skills, and executable tool procedures. When a source artifact is deleted, corrected, or invalidated by tool or API migration, descendants derived from that source can remain visible and steer future actions with stale support. We formalize this failure mode as the cascade update problem, where repair targets the visible derived state of the memory store. We present MemoRepair, a barrier-first cascade-repair contract for agentic memory. A repair event induces a controlled transition from invalidated descendant state to validated successor state: affected descendants are withdrawn before repair, successors are constructed from retained support and staged repaired predecessors under the current interface, and republication is restricted to validated predecessor-closed successors. This contract induces a scalarized repair-selection problem for a fixed repair-cost tradeoff. We show that the induced publication problem reduces to maximum-weight predecessor closure and can be solved exactly by a single s-t min-cut. Experiments on ToolBench and MemoryArena show that, with complete influence provenance, MemoRepair reduces invalidated-memory exposure from 69.8-94.3% under systems without cascade repair to 0%. Compared with exhaustive Repair all, it recovers 91.1-94.3% of validated successors while reducing normalized repair-operator cost from 1.00 to 0.57-0.76.