Metraipolis › archive › dc_d66cabccb344

Multi-Aspect Runtime Verification for Simulation-Based V&V of LLM-Enabled Autonomous Agents — arXiv:2610.08928

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.08928
License (as archived)
CC0-1.0
Archived
2026-10-08T11:10:20.020Z
SHA-256 of the archived text
5dbf980a4f4e488c022431c23b90395d387f6abad5deaabe5edc11f5ec2e5ec5
Stable URL of this page
https://metraipolis.com/documento/dc_d66cabccb344

How to cite

Multi-Aspect Runtime Verification for Simulation-Based V&V of LLM-Enabled Autonomous Agents — arXiv:2610.08928 — arXiv (en), https://arxiv.org/abs/2610.08928 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d66cabccb344 (Metraipolis archive dc_d66cabccb344, sha256 5dbf980a4f4e488c022431c23b90395d387f6abad5deaabe5edc11f5ec2e5ec5)
BibTeX
@misc{dcd66cabccb344,
  title = {Multi-Aspect Runtime Verification for Simulation-Based V&V of LLM-Enabled Autonomous Agents — arXiv:2610.08928},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08928},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d66cabccb344; sha256 5dbf980a4f4e488c022431c23b90395d387f6abad5deaabe5edc11f5ec2e5ec5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08928. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-based agents are entering decision-support roles in defence staff work, where the obligations they must respect are already written down and binding, and where retraining is not available as a control because models arrive as procured components. What can be placed under engineering control is the interface between the agent and the systems it acts on. Those obligations are at once spatial, temporal and text-semantic, and a violation typically lives in the composition of a multi-step interaction, which is why per-event guardrails miss sequential tool-attack chains. We present a multi-aspect runtime-verification framework that decomposes a natural-language policy clause into a typed spatial/temporal/semantic triple over one canonical event stream, checks each aspect with its own monitoring specification, and fuses the verdicts through a four-valued algebra that carries provenance. The spatial aspect is interpreted over a weighted two-sorted location graph in which mission geometry and information-release topology are one object; we show that these spatial obligations are not in general subsumed by a first-order temporal specification. The past-time aspect runs on the unmodified MonPoly engine, which agrees with our reference monitor at every time point. Across two mission domains, casualty evacuation and contested sustainment, and one civil domain, composition under the precautionary blocking policy drives attack success to zero with no observed false positives and microsecond-scale per-event cost, while every single aspect and every pair leaves a substantial share of attacks succeeding. In a closed-loop experiment a policy-naive planner reaches a violating state in most unshielded missions and in none when shielded, and four refused episodes in five still recover to a compliant outcome.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO).
Pagina del lavoro: https://arxiv.org/abs/2610.08928 — 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 2026-10-08T10:14:06.026Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).