Metraipolis › archive › dc_2e44905cf0bd

Policy-as-logic for robust reasoning over rules — arXiv:2608.11905

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.11905
License (as archived)
CC0-1.0
Archived
2026-10-19T05:15:30.852Z
SHA-256 of the archived text
0b7050b74b1683a1f66e9b201626bbad9805ec622760e906fd8d2f3ca38684f1
Stable URL of this page
https://metraipolis.com/documento/dc_2e44905cf0bd

How to cite

Policy-as-logic for robust reasoning over rules — arXiv:2608.11905 — arXiv (en), https://arxiv.org/abs/2608.11905 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2e44905cf0bd (Metraipolis archive dc_2e44905cf0bd, sha256 0b7050b74b1683a1f66e9b201626bbad9805ec622760e906fd8d2f3ca38684f1)
BibTeX
@misc{dc2e44905cf0bd,
  title = {Policy-as-logic for robust reasoning over rules — arXiv:2608.11905},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11905},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2e44905cf0bd; sha256 0b7050b74b1683a1f66e9b201626bbad9805ec622760e906fd8d2f3ca38684f1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11905. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In many practical applications of generative AI systems, from tax rules to airline baggage allowance, responses to natural language queries must respect written policies or rules. We present a hybrid symbolic approach that expresses policies in formal logic and at inference time exploits the representation power of language models for fact extraction to ground predicates, and an answer set solver for reasoning such that responses are interpretable, auditable, and as we show, accurate and robust under input perturbations. Specifically, we show this separation of extraction and reasoning steps outperforms policy-as-prompt and policy-as-code methods in most cases with ~10x reduction in token usage. The results point to the value of structured reasoning and symbolic solvers in conjunction with generative models to make robust decisions involving objective criteria.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Symbolic Computation (cs.SC).
Pagina del lavoro: https://arxiv.org/abs/2608.11905 — 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 2026-10-19T05:08:46.646Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).