Year: 2026
Type: preprint
Abstract: Agent safety in high-stakes domains requires formal policy enforcement, but most existing approaches either rely on probabilistic guardrails (fine-tuned classifiers, prompt-based steering) that offer no formal guarantees, or on hand-coded symbolic enforcement that does not scale to the breadth of real policy specifications. We present an autoformalization pipeline that translates agent prompts, MCP tool descriptions, and natural language policy documents into formally verified policies using an LLM-based generator-critic loop. The resulting policies are written in the Cedar Policy Language. On the MedAgentBench benchmark, our autoformalized policies cover substantially more of the source natural-language specification than the hand-coded symbolic enforcement in prior work.
Source: arXiv (Cornell University)
Authors: Mondl, Adam, Maisel, Matthew, Brock, John H.
Topic: Access Control and Trust
Subfield: Sociology and Political Science
Field: Social Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7166098801
Cites:
Cited by:
Related to: