LLM Digest
Subscribe

Story

arxiv_agent_systems_research · Nov 2, 2026 · paper

Source brief

LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents

arxiv.orgNov 2, 2026
original source linked

In brief

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

Continue reading

Read the original at arxiv.org →Open in live feedRead that day’s brief

Earlier in this thread 4 items