Tool Access Control for LLM Agents

LLM: Large Language Model

Overview

This field studies how to ensure an LLM agent uses only the tools and permissions justified by a user's task, across settings such as APIs, browsers, coding environments, and MCP-based systems. Common approaches include task-scoped least-privilege policies, capability-based delegation, provenance and information-flow tracking, and runtime gateways that check calls before execution or commit; human approval is often reserved for consequential actions. Evidence shows that prompts and static tool allowlists can leave gaps, especially when calls change meaning across steps, permissions persist, or authorization is not bound to the exact action and current state. A central challenge is balancing strong, verifiable restrictions with useful autonomy, while evaluating both unauthorized effects and unnecessary denials in realistic, long-running workflows.

Latest papers

CardsList

255 papers43 papers in the last four weeks, down 10% on the four weeks before. 0.3% of all new papers.

  1. WebAgents: Unbundling Agent Creation, Hosting, and Execution for an Agent-Native Web

    Nov 16, 2026Dario Fenoglio, Martin Gjoreski, Marc Langheinrich +2Web AgentsAI Agent Interoperability

  2. Procedure without Judgment: What Small Language Models Learn under an Exact Verifier

    Nov 16, 2026Arunkumar V, Manoranjan Gandhudi, Gangadharan G. R. +2llm agent policy complianceConcept-Based Explanations

  3. Evaluating Authorization and Trust Boundaries in Agentic Orchestration Frameworks

    Nov 16, 2026Sahaya Jestus Lazer, Kshitiz Aryal, Maanak Gupta +1AI Agent SecurityTool Access Control for LLM Agents

  4. Recovery Gone Too Far: Understanding and Repairing Risky Fallback in LLM Agents

    Nov 15, 2026Liwen Wang, Jiangrong Wu, Zongjie Li +3LLM Agent SafetyTool Access Control for LLM Agents

  5. Auditable Authorization for LLM Agents: Empirical Evidence Across Model, Harness, and Workflow Layers

    Nov 14, 2026Bangjie Deng, Xiaoxuan Lu, Wenjun Chen +8AI Agent AuditingHuman Oversight of AI

  6. Soteria: Formally Verified Planning with Runtime Enforcement for Safe LLM Agents

    Nov 13, 2026Mike He, Ankush Desai, Sharad Malik +1LLM Agent SafetyLLM Agent Planning

  7. guardscope: Measuring Which Actions Runtime Controls Check in LLM Agent Systems

    Nov 11, 2026Kentaroh Toyoda, Alex Leung, Bhuvaneswari URuntime Enforcement for AI AgentsAI Agent Auditing

  8. From Attack Surface to Defense Architecture: Compositional Security for Agentic Coding Harnesses

    Nov 10, 2026Simon Hegelich, Bardh Prenkaj, Habiba Sarhan +5AI Agent SecurityTool Access Control for LLM Agents

  9. DEPUTYBENCH: Evaluating Contextual Safety in Enterprise Agents

    Nov 9, 2026Hao Zhao, Minghao LinAI Agent Security BenchmarksLLM Agent Safety

  10. ShadowBench-MCP: Measuring Shadow Invocations in MCP-Style Tool Routing

    Nov 9, 2026Eyhab Al-Masri, Wenjun YangLLM Agent SecurityLLM Routing

  11. Treating the Model as an Untrusted Component: Deterministic Policy Enforcement, Human Approval and Taint Tracking Against Prompt Injection in Tool-Using Agents, with Validation on Open-Weights Models

    Nov 8, 2026Mustafa S. Aljumaily, Nawar S. Alseelawi, Raghad AlshabandarPrompt Injection DefenseLLM Agent Safety

  12. Safeguarding Agentic AI in Radiology Workflows: A Multimodel Evaluation of Rule-based and Large Language Model-based Verification

    Nov 8, 2026Semil Eminovic, Robin Schmidt, Bogdan Levita +3LLM Agent SafetyLLM Guardrails

  13. Authorization Drift in LLM Agents: Evaluating Boundary Compliance in Multi-Step Tool Use

    Nov 6, 2026Chuxue Cao, Jingru Zeng, Boqin Yin +7LLM Agent SafetyTool Access Control for LLM Agents

  14. From Procedures to Permissions: Learning Precise Subagent Authorization from Agent Skills

    Nov 6, 2026Wenkai Yu, Ning Ding, Wentao Zhang +1LLM Agent OrchestrationTool Access Control for LLM Agents

  15. The Power of Meta Access in the Software of the Future --- Demonstrated on LLM Chat UIs and Chat AI

    Nov 5, 2026Julian Kunkel, Ali DoosthosseiniTool Access Control for LLM Agents

  16. SecureGARD: Dynamic Ontology-Guided Governance for Secure Tool-Using LLM Agents

    Nov 4, 2026Guoqin Xiong, Shengtao Wen, Xiang Chen +5AI Agent SecurityTool Access Control for LLM Agents

  17. When Do Summaries Become Instructions? Unsupported Policy in LLM Agents' Self-Written Handoff Summaries

    Nov 4, 2026Wenhui ChuLLM Agent SafetyTool Access Control for LLM Agents

  18. Networked Synthetic Social Engineering on the Web

    Nov 2, 2026Bryan C. BootsAI Agent SecurityTool Access Control for LLM Agents

  19. LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents

    Nov 2, 2026Sreehari Sankar, Debargha Ganguly, Vikash Singh +17Tool Access Control for LLM AgentsLLM Guardrails

  20. Accessed, never disclosed: Silent access to protected health information by medical artificial intelligence agents

    Nov 2, 2026Jae Wang Lee, Abhirup Banerjee, Yeong Chan LeeMedical AI AgentsPrivacy Protection for LLM Agents

  21. Dependable Agents Need Hard and Fuzzy Rules

    Oct 31, 2026Frederick RothLLM GuardrailsRuntime Enforcement for AI Agents