Metraipolis › archive › dc_4bb1db9917bf
From Natural Language Policies to Executable Obligations: A Verification Harness for Dependable In-Car LLM Agents — arXiv:2608.23282
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.23282
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T08:12:51.965Z
- SHA-256 of the archived text
e399f5ba5003e9734649681e919439ee6429eae3f9459b223f3e3710d81009b4- Stable URL of this page
https://metraipolis.com/documento/dc_4bb1db9917bf
How to cite
From Natural Language Policies to Executable Obligations: A Verification Harness for Dependable In-Car LLM Agents — arXiv:2608.23282 — arXiv (en), https://arxiv.org/abs/2608.23282 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4bb1db9917bf (Metraipolis archive dc_4bb1db9917bf, sha256 e399f5ba5003e9734649681e919439ee6429eae3f9459b223f3e3710d81009b4)
BibTeX
@misc{dc4bb1db9917bf,
title = {From Natural Language Policies to Executable Obligations: A Verification Harness for Dependable In-Car LLM Agents — arXiv:2608.23282},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.23282},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4bb1db9917bf; sha256 e399f5ba5003e9734649681e919439ee6429eae3f9459b223f3e3710d81009b4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23282. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large Language Models (LLMs) agents deployed in vehicles must satisfy a written operating policy on every turn: a single hallucinated identifier, omitted mandatory side-effect, or premature completion claim fails the task. We present AgentGuardUtil, our entry to CAR-bench Track~1, which treats the AI planer (LLM) as a fallible proposer inside a grounded verify-and-revise loop. Its core novelty is a runtime policy compiler: the natural-language policy shipped with each conversation is compiled, once per policy, into typed machine-checkable rules, a subset of which receive an executable form. A deterministic obligation engine interprets these rules against live tool results and the simulated post-write state of the draft itself, emitting the exact remedial calls with computed arguments rather than natural-language reminders. Around this engine, 25 deterministic gates (identifier provenance, schema and enum validity, gather-before-act, confirmation and future-time protocols) and an LLM critic produce tiered findings that drive a bounded revision loop tuned for the pass k metric. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-25 in cs.SE). Categorie arXiv: Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2608.23282 — 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 2026-10-18T08:07:33.022Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).