Search papers, labs, and topics across Lattice.
To determine when stale or misaligned procedural memory causes negative transfer, the authors evaluated whether deliberately mismatched frozen routines disrupt language agents across 32 controlled synthetic web-shopping tasks spanning four distinct mismatch regimes. Counter to expectations of memory-induced behavioral interference, none of the predefined error signatures emerged across the formal test cells when current-task evidence was explicit and sufficient. This reveals an empirical "region of non-interference," demonstrating that language agents can robustly override obsolete procedural priors without requiring explicit memory-unlearning mechanisms.
Outdated procedural memories do not inherently degrade agent performance: language models reliably prioritize grounded in-context evidence over conflicting historical routines across diverse task perturbations.
Procedural memory lets language agents reuse successful routines, but reuse presumes that a stored routine remains applicable. We study what happens when that presumption is deliberately violated. The study combines a retrospective, human-assisted interface-adaptation case from BrowserGym TimeWarp with 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 while the no-memory condition selected the reference minimum. Follow-up probes did not establish 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 one 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. It does not establish general safety or a mechanism. The remaining question is which additional conditions turn applicability mismatch into observable, memory-caused error.
