Metraipolis › archive › dc_509f2d18dc43

Beyond Corrected Memory: Execution Consistency in Multi-Agent Systems — arXiv:2610.08101

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.08101
License (as archived)
CC0-1.0
Archived
2026-10-07T11:19:25.247Z
SHA-256 of the archived text
ee1966e906de4cdb39654891c226b7b5973f23d30bd1be05e04bb19b7e267e02
Stable URL of this page
https://metraipolis.com/documento/dc_509f2d18dc43

How to cite

Beyond Corrected Memory: Execution Consistency in Multi-Agent Systems — arXiv:2610.08101 — arXiv (en), https://arxiv.org/abs/2610.08101 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_509f2d18dc43 (Metraipolis archive dc_509f2d18dc43, sha256 ee1966e906de4cdb39654891c226b7b5973f23d30bd1be05e04bb19b7e267e02)
BibTeX
@misc{dc509f2d18dc43,
  title = {Beyond Corrected Memory: Execution Consistency in Multi-Agent Systems — arXiv:2610.08101},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08101},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_509f2d18dc43; sha256 ee1966e906de4cdb39654891c226b7b5973f23d30bd1be05e04bb19b7e267e02},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08101. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Shared memory coordinates agents' actions, but correct records do not establish that those actions satisfy task requirements. Memory governance and failure diagnosis regulate or inspect recorded information; they do not by themselves establish whether it is sufficient to judge task duties. We define execution consistency through duties governing state use, information handoffs, and final-state agreement, with explicit evidence conditions for judging fulfillment. Our core claim is that identical retained records can correspond to compliant and violating executions under the same task rule. Controlled removal of evidence such as receipt, action dependence, or response validity leaves 82.4% of opposite-label pairs indistinguishable; restoration separates 97.9% of the merged pairs. Natural-log annotations identify the defined violations in actual executions. However, existing logs do not always explicitly represent the execution relationships needed for these judgments. To assess the definition's practical value, we use CAVERT, a framework for consistency diagnosis and recovery, to extract supported relationships from logs and apply these criteria. It consistently outperforms contract-prompted LLM and rule-based baselines in diagnosis across all 12 benchmark-executor settings. Under the same gate and executor limits, it also outperforms rule-guided recovery in all four evaluated environments. These findings identify execution evidence that agent-memory and execution interfaces should preserve for reliable judgment.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.08101 — 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 2026-10-07T11:15:24.584Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).