mlsanityData to 7 Oct 2026

Towards Enforcing Company Policy Adherence in Agentic Workflows

arXiv 2507.16459 ↗First posted 22 Jul 2025cs.CLcited by 17

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

Large Language Model (LLM) agents hold promise for a flexible and scalable alternative to traditional business process automation, but struggle to reliably follow complex company policies. In this study we introduce a deterministic, transparent, and modular framework for enforcing business policy adherence in agentic workflows. Our method operates in two phases: (1) an offline buildtime stage that compiles policy documents into verifiable guard code associated with tool use, and (2) a runtime integration where these guards ensure compliance before each agent action. We demonstrate our approach on the challenging τ-bench Airlines domain, showing encouraging preliminary results in policy enforcement, and further outline key challenges for real-world deployments.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 23 of its 39 references that are in the map. First posted on arXiv 22 Jul 2025.

Builds on

23 of 39 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Effective Red-Teaming of Policy-Adherent Agents11 Jun
  2. 2025LlamaFirewall: An open source guardrail system for building secure AI agents6 May
  3. 2024Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In22 Oct
  4. 2024ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents9 Oct
  5. 2024TrustAgent: Towards Safe and Trustworthy LLM-based Agents2 Feb

Other references · 18

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  6. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  7. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,280
  8. 2020CodeBLEU: a Method for Automatic Evaluation of Code Synthesiscited by 468
  9. 2024TradingAgents: Multi-Agents LLM Financial Trading Frameworkcited by 182
  10. 2023Conversational Health Agents: A Personalized LLM-Powered Agent Frameworkcited by 91
  11. 2022Execution-Based Evaluation for Open-Domain Code Generationcited by 89
  12. 2023Attention Sorting Combats Recency Bias In Long Context Language Modelscited by 89
6 more
  1. 2024CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environmentscited by 69
  2. 2024Large Language Model Agent in Financial Trading: A Surveycited by 60
  3. 2024Understanding Biases in ChatGPT-based Recommender Systems: Provider Fairness, Temporal Stability, and Recencycited by 27
  4. 2025Assessing and Advancing Benchmarks for Evaluating Large Language Models in Software Engineering Taskscited by 17
  5. 2024Alignment Studio: Aligning Large Language Models to Particular Contextual Regulationscited by 10
  6. 2024Procedural Adherence and Interpretability Through Neuro-Symbolic Generative Agentscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 17.

17 papers.

Sort:

By area:

  1. 2026PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agentscited by 5
  2. 2026Near-Miss: Latent Policy Failure Detection in Agentic Workflowscited by 4
  3. 2026Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systemscited by 3
  4. 2026Mind the GAP: Text Safety Does Not Transfer to Tool-Call Safety in LLM Agentscited by 2
  5. 2026Tool-Making and Self-Evolving LLM Agents in Low-Latency Systemscited by 2
  6. 2026HANDBOOK.md: A Benchmark for Long-Context Agentic Instruction Followingcited by 2
  7. 2026PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agentscited by 2
  8. 2026Governance by Construction for Generalist Agentscited by 1
  9. 2026Benchmarking the Benchmarks: Evaluating Benchmarks for Conversational Agentscited by 1
  10. 2026DRIP-R: A Benchmark for Decision-Making and Reasoning Under Real-World Policy Ambiguity in the Retail Domaincited by 0
  11. 2026When Retrieval Metrics Mislead: Measuring Policy Signal in Long-Horizon Tool-Use Agentscited by 0
  12. 2026FRAMES: Guarded and Dual-Objective Skill Evolution for Agents in Policy-Governed Enterprise Workflowscited by 0
5 more
  1. 2026STAGE: Stateful Translation to Agentic Graph Execution with Policy-Scoped Context and Deterministic Controlcited by 0
  2. 2026Policy Loopholes in Agent Evaluation: When Policy Ambiguity Masquerades as Agent Errorcited by 0
  3. 2026From Alignment to Access Control: A Framework for GenAI Policy Enforcementcited by 0
  4. 2026Authorization Closure Graph: Minimal Repair for LLM Agents with Evolving User Instructionscited by 0
  5. 2026NOMOS: Compiling Written Policies into Statically Verified Tool-Call Gates for LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Solver-Aided Verification of Policy Compliance in Tool-Augmented LLM Agents
  2. 2026ActGov: Governing LLM Agent Actions via Policy-Constrained Validation
  3. 2026Authenticated Workflows: A Systems Approach to Protecting Agentic AI
  4. 2026Policy-Invisible Violations in LLM-Based Agents
  5. 2026Maat: Independent Deterministic Contract-Based Governance for Multi-Agent LLM Workflows
  6. 2026AgentFlow: A Flow-Centric Policy Language and Framework for Securing LLM Agent Systems
  7. 2026MANTRA: Synthesizing SMT-Validated Compliance Benchmarks for Tool-Using LLM Agents
  8. 2025FlowAgent: Achieving Compliance and Flexibility for Workflow Agents