Metraipolis › archive › dc_bcd377d6d4f2

Invalidation Contracts for Cross-Episode Agent Memory — arXiv:2609.00243

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00243
License (as archived)
CC0-1.0
Archived
2026-10-17T06:31:44.635Z
SHA-256 of the archived text
365fa5769721801e647cde4202d3a84693021a1dba36fa4799047efab706a642
Stable URL of this page
https://metraipolis.com/documento/dc_bcd377d6d4f2

How to cite

Invalidation Contracts for Cross-Episode Agent Memory — arXiv:2609.00243 — arXiv (en), https://arxiv.org/abs/2609.00243 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bcd377d6d4f2 (Metraipolis archive dc_bcd377d6d4f2, sha256 365fa5769721801e647cde4202d3a84693021a1dba36fa4799047efab706a642)
BibTeX
@misc{dcbcd377d6d4f2,
  title = {Invalidation Contracts for Cross-Episode Agent Memory — arXiv:2609.00243},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00243},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bcd377d6d4f2; sha256 365fa5769721801e647cde4202d3a84693021a1dba36fa4799047efab706a642},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00243. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM agents that cache recovery suggestions from API errors can skip re-derivation in later episodes, spending fewer tokens and fewer model calls on constraints they have already learned. Server-side data drift turns those cached fixes into silent failures, and the usual remedy, re-deriving on every episode, gives the savings back. We introduce invalidation contracts, a protocol layer that attaches version stamps and cacheability hints to every recovery suggestion so the client can evict stale entries without trial and error, and keep the rest. The contract decomposes realized savings into two independent factors: validity, the fraction of cached suggestions that remain correct after a drift event, and compliance, the fraction the planner applies on the first attempt. Validity depends only on the protocol and is vendor-independent. Compliance depends on the planner model: identical wire bytes yield 100% first-try compliance on Claude Haiku 4.5 and 11% or below on Claude Sonnet 5, which exhibits input-schema conservatism, refusing fixes that add fields the original request did not contain. We evaluate across seven models, three serving paths, two domains, and approximately 9,400 episodes. Row-level invalidation raises compliance by 0 to 66.7 percentage points across the seven models, 55.6 to 66.7 on three, and recovers 29-33% of baseline token cost on four of seven models, while table-level invalidation destroys co-located entries and drops post-drift first-try rates to 0% on five of seven. Eviction precision is 1.00 at row granularity on every model under the row-level oracle of Section 4.1. The contract adds 15% to response payload. Version-stamp validity is deterministic by construction and produced identical results across every model and serving path, with zero contract failures in the entire evaluation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.00243 — 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 2026-10-17T06:15:12.574Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).