LeaseGuard: Incumbent-Preserving Admission Control for Privileged LLM Agents

arXiv:2609.24077 · cs.CR · Submitted 2026-09-21 · Read on arXiv

cs.CR

Submitted: 2026-09-21

Updated: 2026-09-21

Comments: 6 pages, 2 figures, 4 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 7× in this paper · explained in 2 episodes
• AI Agents — 4× in this paper · explained in 2 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Agentic Workflows — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Analyzer — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Formal Verification — 1× in this paper · explained in 2 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Post-Selection — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• ClashBench: Conflicts Leading Agents to Seize and Harm
• VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills
• Sovereign Execution Broker: Enforcing Certificate-Bound Authority in Agentic Control Planes
• AgentCgroup: Understanding and Controlling OS Resources of AI Agents
• Reason Less, Verify More: Deterministic Gates Recover a Silent Policy-Violation Failure Mode in Tool-Using LLM Agents
• The Verifier Tax: Horizon Dependent Safety Success Tradeoffs in Tool Using LLM Agents
• Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows
• Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems
• Progent: Securing AI Agents with Privilege Control
• Beyond OAuth: Task-Scoped Authorization for AI Agents via Natural Language Slices
• Alignment Contracts for Agentic Security Systems
• Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents
• AgenticOS: An Intent-Oriented Secure Operating System Architecture for Autonomous AI Agents
• Agentic Workflows for Resolving Conflict Over Shared Resources: A Power Grid Application
• Qwen3 Technical Report

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs