Metraipolis › archive › dc_d44647b81dff

When Is an Agent Evaluation Over? Outcome Finality and Cross-Unit Separation — arXiv:2608.14940

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14940
License (as archived)
CC0-1.0
Archived
2026-10-18T17:08:13.816Z
SHA-256 of the archived text
926f6f286173ae1a5775555f5056b691d7595c46f4c69d11445c243ebd5cab99
Stable URL of this page
https://metraipolis.com/documento/dc_d44647b81dff

How to cite

When Is an Agent Evaluation Over? Outcome Finality and Cross-Unit Separation — arXiv:2608.14940 — arXiv (en), https://arxiv.org/abs/2608.14940 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d44647b81dff (Metraipolis archive dc_d44647b81dff, sha256 926f6f286173ae1a5775555f5056b691d7595c46f4c69d11445c243ebd5cab99)
BibTeX
@misc{dcd44647b81dff,
  title = {When Is an Agent Evaluation Over? Outcome Finality and Cross-Unit Separation — arXiv:2608.14940},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14940},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d44647b81dff; sha256 926f6f286173ae1a5775555f5056b691d7595c46f4c69d11445c243ebd5cab99},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14940. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agent evaluations commonly score the state observed when a run stops and count the run as one trial. Interpreting that score as a final result from a separate trial requires outcome finality and cross-unit separation. Outcome finality requires that later events cannot change the claimed result, while cross-unit separation requires that earlier runs cannot change the relevant conditions of later ones. The endpoint establishes neither condition by itself, and the two can hold independently. Waiting for a delayed outcome may settle the label even though its state remains available to another run. Isolation may prevent carryover even though the scored outcome remains unresolved. We develop a completion argument that identifies the evidence needed for each decision. A final success or failure label is justified only when every relevant effect is resolved or bounded tightly enough to fix the outcome. Any remaining uncertainty must be reported. First, in a controlled replay with fixed agent actions, we find that endpoint and terminal labels differ for every nonzero-delay operation and that a delayed write changes the next run's score under shared state but has no such effect after namespacing or verified reset. Second, in a review of ten public protocols, we find that reset or deliberate retention is documented explicitly more often than unfinished operations or evidence for separate scoring. Finally, we propose an open-effects record for operations and resources that may remain relevant after the endpoint, their status, and their possible effects on the scored outcome or another run.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2608.14940 — 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 2026-10-18T16:29:13.748Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).