mlsanityData to 14 Oct 2026

From Natural Language Policies to Executable Obligations: A Verification Harness for Dependable In-Car LLM Agents

arXiv 2608.23282 ↗First posted 24 Aug 2026cs.SEcited by 0

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 3 of its 4 references that are in the map. First posted on arXiv 24 Aug 2026.

Builds on

3 of 4 references.

References · 3

  1. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 324
  2. 2023Better patching using LLM prompting, via Self-Consistencycited by 29
  3. 2026CAR-bench: Evaluating the Consistency and Limit-Awareness of LLM Agents under Real-World Uncertaintycited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Watchdogs and Oracles: Runtime Verification Meets Large Language Models for Autonomous Systems
  2. 2026ActGov: Governing LLM Agent Actions via Policy-Constrained Validation
  3. 2026Verification as an Architectural Layer for LLM Agents: A V-Model Design, and a Pilot Study of Its Deterministic Core
  4. 2026Harnessing LLMs as Agents: What Does It Cost?
  5. 2026PolicyBank: Evolving Policy Understanding for LLM Agents
  6. 2026LOGIGEN: Logic-Driven Generation of Verifiable Agentic Tasks
  7. 2026Autoformalization of Agent Instructions into Policy-as-Code
  8. 2026MANTRA: Synthesizing SMT-Validated Compliance Benchmarks for Tool-Using LLM Agents