Procedural memory enables language agents to reuse successful routines, assuming the stored routine remains applicable. This work deliberately violates that assumption to see what happens. The study has two parts: a retrospective, human‑assisted interface‑adaptation case from BrowserGym TimeWarp, and controlled frozen‑memory comparisons on synthetic shopping decisions.
During the documented WebShop V1‑V6 development path, interface‑specific code was adapted while the separately stored high‑level procedure was not reported to change; this phase does not constitute an autonomous memory‑agent evaluation. In the controlled phase, an early pilot produced one task on which two memory conditions selected a more expensive item, whereas the no‑memory condition chose the reference minimum. Follow‑up probes did not reveal a recurring row order or identity‑binding pattern.
We then tested four forms of mismatch: changed quantities, a different evidence representation, a conflict between local and global optimization, and distributed promotion evidence, across 32 formal cells. Each cell used a single temperature‑0 generation with the same local qwen3:8b configuration and no adaptive retry. Across these pairs, none of the predefined diagnostic interference signatures appeared on the tasks for which they were defined when current‑task evidence was explicit and sufficient.
The result identifies a tested region of non‑interference: a procedural memory can be mismatched without becoming behaviorally disruptive. This does not establish general safety or a mechanism. The remaining question is which additional conditions turn applicability mismatch into an observable, memory‑caused error.
Review