Metraipolis › archive › dc_b7c56fe42e79

Can Semantic Geometry Teach an AI Judgement? — arXiv:2610.07249

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07249
License (as archived)
CC0-1.0
Archived
2026-10-07T11:18:27.821Z
SHA-256 of the archived text
752afaf7363c5c91cbb0d6be6f20a2e145fbab6f138578eff09011a1a75d20ee
Stable URL of this page
https://metraipolis.com/documento/dc_b7c56fe42e79

How to cite

Can Semantic Geometry Teach an AI Judgement? — arXiv:2610.07249 — arXiv (en), https://arxiv.org/abs/2610.07249 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b7c56fe42e79 (Metraipolis archive dc_b7c56fe42e79, sha256 752afaf7363c5c91cbb0d6be6f20a2e145fbab6f138578eff09011a1a75d20ee)
BibTeX
@misc{dcb7c56fe42e79,
  title = {Can Semantic Geometry Teach an AI Judgement? — arXiv:2610.07249},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07249},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b7c56fe42e79; sha256 752afaf7363c5c91cbb0d6be6f20a2e145fbab6f138578eff09011a1a75d20ee},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07249. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

How can an AI agent determine what rules to follow? One rule permits an action. Another imposes a condition, exception, or conflicting obligation. Deterministic systems can resolve those relationships when they have been specified. When they remain implicit in language, an agent can follow one rule while missing another that should stop it. Refusing every unresolved action avoids that risk, but also blocks permissible actions. We wanted the agent to make the distinction and still act. Our initial hypothesis was that geometric measurements could supply a basis for judgment. We represented actions and policies as vectors, then tested whether their geometry could identify governing policies and interpret the action's relation to them. Across four studies, the tested approaches did not establish reliable pre-action judgment. In the final synthetic study, a lexical router recovered every governing and blocking policy while reducing median policy checks by 97.7%. The composed pipeline nevertheless escalated all 2,304 test actions, including those it should have allowed. Supplying every policy to the same downstream mechanism changed no decision. Finding the policies had not solved the problem of interpreting them. This result led us to revise our hypothesis: judgment in AI agents requires developing a consequence graph. Such a graph would connect the actor and authority to policy conditions, exceptions, and the changes an action would produce. Follow-on studies will ask whether making those relationships explicit helps the agent distinguish when to act, stop, or seek review.

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/2610.07249 — 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 2026-10-07T11:15:24.487Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).