AI RESEARCH
MEMOREPAIR: Barrier-First Cascade Repair in Agentic Memory
arXiv CS.AI
•
ArXi:2605.07242v1 Announce Type: new 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. We formalize this failure mode as the cascade update problem, where repair targets the visible derived state of the memory. We present MemoRepair, a barrier-first cascade-repair contract for agentic memory.