Tool-using language-model agents often execute actions that their domain policies forbid. We present LeanGuard, a runtime that checks every proposed tool call against a policy written in Lean4 before
LeanGuard is a verified runtime that blocks policy-violating tool calls by language-model agents and can repair them via proof-guided search, reducing unauthorized executions and prompt-injection success without harming benign task performance.
Tool-using language-model agents often execute actions that their domain policies forbid. We present LeanGuard, a runtime that checks every proposed tool call against a policy written in Lean4 before the call reaches the environment. Policies combine state predicates with scoped past-time temporal operators over the execution history, evaluation is fail-closed, and the decision procedure is proved equivalent to a LeanLTL semantics. A denied call can be corrected in two ways. With feedback, the agent receives the violated rule and a hint; with proof-guided repair, Lean metaprogramming searches for a nearby call that preserves the user's intent and proves that the policy admits it, without…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents was first seen on Hugging Face · Daily papers on Nov 3, 2026. Since then it has appeared in 9 checks on 2 different days. Its best position was #18 of 30, reached on Nov 4, 05:28 UTC. It dropped off the list after Nov 4, 07:28 UTC.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 4, 07:28 UTC, after 2 days of trending.
#18 on Hugging Face · Daily papers, on Nov 4, 05:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Nov 3, 2026 and has been on the list on 2 days (9 checks) since.