Metraipolis › archive › dc_7114e52f6bae
From Version Conflicts to Decision Conflicts: Selective Revalidation for Long-Running AI Agents — arXiv:2609.08015
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.08015
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:31:37.827Z
- SHA-256 of the archived text
12648667cd2640a9ecf70d434ed1389c86ed5f657d06476faa0062263ad482d6- Stable URL of this page
https://metraipolis.com/documento/dc_7114e52f6bae
How to cite
From Version Conflicts to Decision Conflicts: Selective Revalidation for Long-Running AI Agents — arXiv:2609.08015 — arXiv (en), https://arxiv.org/abs/2609.08015 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7114e52f6bae (Metraipolis archive dc_7114e52f6bae, sha256 12648667cd2640a9ecf70d434ed1389c86ed5f657d06476faa0062263ad482d6)
BibTeX
@misc{dc7114e52f6bae,
title = {From Version Conflicts to Decision Conflicts: Selective Revalidation for Long-Running AI Agents — arXiv:2609.08015},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.08015},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7114e52f6bae; sha256 12648667cd2640a9ecf70d434ed1389c86ed5f657d06476faa0062263ad482d6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08015. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-running AI agents may read state, reason, wait for tools or human approval, and perform an external action much later. The state that justified the action can change in the meantime. For example, after an agent proposes an 80 GBP refund under a limit of 100, a customer-name change affects only presentation metadata, a new limit of 90 still permits the refund, a limit of 50 invalidates it, and a refund issued by another worker must prevent a duplicate. Standard optimistic concurrency control and version checks can detect that previously read state has changed, but by themselves do not determine whether that change invalidates the pending action's justification. We call any detected version change a version conflict; when that change invalidates the action's justification, it is also a decision conflict. ATR records the explicit, executable conditions that justify a pending action and rechecks only the conditions affected by a change before releasing the external operation. It can retain the action, refresh non-decisive metadata, require replanning, or block execution; a target-side transaction or compare-and-set binds checked state to commit. Across 210,000 controlled executions over 15 mutation cases, ATR matched every developer-specified outcome with no false allows or blocks. In ten durable SQLite checkpoint/resume cells, it evaluated 0.6 conditions per change versus 6.0 for FullScan. At 4,093 recorded reads, ATR took 9.3 microseconds versus 2595.9 microseconds for FullScan. These deterministic results establish controlled feasibility, not production generality or automatic extraction of the required conditions. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.DB). Categorie arXiv: Artificial Intelligence (cs.AI) ; Databases (cs.DB). Pagina del lavoro: https://arxiv.org/abs/2609.08015 — 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 2026-10-16T15:12:35.397Z dalla pagina https://arxiv.org/catchup/cs.DB/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).