PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents
cs.AI, cs.CL
Submitted: 2026-06-28
Updated: 2026-11-09
Comments: 21 pages. Updated manuscript with expanded cross-domain evaluation and analyses
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Constitutional AI: Harmlessness from AI Feedback
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
- Formal Policy Enforcement for Agentic Systems
- Near-Miss: Latent Policy Failure Detection in Agentic Workflows
- Solver-Aided Verification of Policy Compliance in Tool-Augmented LLM Agents
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents