PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents
cs.AI, cs.CL, cs.LG
Submitted: 2026-08-20
Updated: 2026-11-09
Comments: 26 pages, 14 figures, including appendices
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Beyond IVR: Benchmarking Customer Support LLM Agents for Business-Adherence
- $\tau^2$-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
- CRMArena-Pro: Holistic Assessment of LLM Agents Across Diverse Business Scenarios and Interactions
- PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents
- IntellAgent: A Multi-Agent Framework for Evaluating Conversational AI Systems
- State Machine of Thoughts: Leveraging Past Reasoning Trajectories for Enhancing Problem Solving
- AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
- 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
- Progent: Securing AI Agents with Privilege Control
- FlowAgent: Achieving Compliance and Flexibility for Workflow Agents
- Solver-Aided Verification of Policy Compliance in Tool-Augmented LLM Agents
- GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- SOP-Agent: Empower General Purpose AI Agent with Domain-Specific SOPs
- ProAgent: From Robotic Process Automation to Agentic Process Automation
- Towards Enforcing Company Policy Adherence in Agentic Workflows
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