Metraipolis › archive › dc_d4e08c168d0a

Procedural Memory Under Change: Reuse and Interference in Controlled Web Tasks — arXiv:2609.09774

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.09774
License (as archived)
CC0-1.0
Archived
2026-10-16T07:24:31.896Z
SHA-256 of the archived text
46995eaaf27dfb855fe436acddf53040e6eb73fce1db97dedc1586ae91edd0ac
Stable URL of this page
https://metraipolis.com/documento/dc_d4e08c168d0a

How to cite

Procedural Memory Under Change: Reuse and Interference in Controlled Web Tasks — arXiv:2609.09774 — arXiv (en), https://arxiv.org/abs/2609.09774 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d4e08c168d0a (Metraipolis archive dc_d4e08c168d0a, sha256 46995eaaf27dfb855fe436acddf53040e6eb73fce1db97dedc1586ae91edd0ac)
BibTeX
@misc{dcd4e08c168d0a,
  title = {Procedural Memory Under Change: Reuse and Interference in Controlled Web Tasks — arXiv:2609.09774},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09774},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d4e08c168d0a; sha256 46995eaaf27dfb855fe436acddf53040e6eb73fce1db97dedc1586ae91edd0ac},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09774. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.09774 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T07:00:16.215Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).