PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents
LLM agents handle user requests on behalf of organizations through tool calls and must follow the company policies stated in their system prompts. Prior work approaches this as a safeguarding problem -- external checks that block non-compliant agent actions. We argue that policy adherence is a broader problem: real workflows unfold across many turns, require explicit user confirmation and prerequisite reads, and hinge on the content of the dialogue rather than on any single argument value. Meeting this bar requires (i) full conversation context, (ii) self-reasoning over the policy and the curr
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownagent-tools →
- LinkedLinked via unknownProduction-grade AI agents for financial compliance: Lessons from Stripe →
- FuzzySimilar title/name (fuzzy) · 59%AgentCore-8B →
“Fuzzy title match (0.73): “PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Poli” ≈ “AgentCore-8B””
- PossiblePossibly related (embedding) · 59%antoinezambelli/forge →
- FuzzySimilar title/name (fuzzy) · 87%SWE-agent/SWE-agent →
“Fuzzy title match (0.94): “PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Poli” ≈ “SWE-agent/SWE-agent””
- FuzzySimilar title/name (fuzzy) · 87%zhayujie/CowAgent →
“Fuzzy title match (0.94): “PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Poli” ≈ “zhayujie/CowAgent””