Metraipolis › archive › dc_88cab27ff697

PRIME: Towards Verifiable Evidence-Grounded Reasoning in LLM Agents — arXiv:2610.22426

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22426
License (as archived)
CC0-1.0
Archived
2026-10-19T08:42:04.395Z
SHA-256 of the archived text
6cfe733e3e55339d79dee4377f1e4f9689a7841d46f8ca18a810da4f903c8539
Stable URL of this page
https://metraipolis.com/documento/dc_88cab27ff697

How to cite

PRIME: Towards Verifiable Evidence-Grounded Reasoning in LLM Agents — arXiv:2610.22426 — arXiv (en), https://arxiv.org/abs/2610.22426 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_88cab27ff697 (Metraipolis archive dc_88cab27ff697, sha256 6cfe733e3e55339d79dee4377f1e4f9689a7841d46f8ca18a810da4f903c8539)
BibTeX
@misc{dc88cab27ff697,
  title = {PRIME: Towards Verifiable Evidence-Grounded Reasoning in LLM Agents — arXiv:2610.22426},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22426},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_88cab27ff697; sha256 6cfe733e3e55339d79dee4377f1e4f9689a7841d46f8ca18a810da4f903c8539},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22426. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM agents are used to check records against an organization's requirements, for example whether a vulnerability report is ready for investigation. Requirements often allow several ways to be met, such as a severity rating with a curator-reviewed advisory or a published advisory link. Agents fail by accepting a report after a required check has failed, or by settling for a weaker conclusion without trying another way that could still succeed. We introduce PRIME (Precommitted Rules for Inference from Minimal Evidence). Before checking, it fixes evidence routes specifying how each conclusion may be justified. A separate program records each check result and refuses any conclusion the results do not justify. It also points the agent to checks that could justify a stronger conclusion, or runs them itself. PRIME reports only conclusions authorized by its rules and ledger. With correct requirements, exact checks at known locations, and sufficient budget at stopping, completion reaches the strongest supported conclusion. On 480 public-record tasks, an agent shown the requirements reported unjustified conclusions on 26.7% of tasks, while PRIME reported none. Its directions and added checks raised the average score for justified conclusions from 30.1, with refusal alone, to the maximum of 59.2 out of 100.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.22426 — 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 2026-10-19T08:39:10.000Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).