LeaseGuard: Incumbent-Preserving Admission Control for Privileged LLM Agents
On the map: LLM agents and tool use → Agent threats, guardrails and governance
Abstract (arXiv)
Privileged language-model agents can satisfy a new system task by displacing a healthy incumbent that depends on the same file, process, socket, lock, or capacity allocation. This failure arises because execution privilege determines whether an operation can run, not whether the requester may preempt the current resource owner. We present LeaseGuard, a deterministic admission layer that represents preemption authority through canonical resource leases, incumbent-health checks, effect-aware admission, coexistence limits, safe alternatives, and resource-scoped overrides before adapter execution. We evaluate it on a frozen benchmark of 60 newly authored conflict scenarios with matched controls across two local model families. Relative to a preservation prompt, LeaseGuard reduces unauthorized preemption from 73.3% to 0.0% and increases safe completion by 70.0 percentage points (scenario-clustered 95% CI [60.8, 79.2]). Requested-task success changes by -3.3 points (95% CI [-9.2, 2.5]). The fully evaluated v0.2 broker also rejects a forged incumbent task identity in a hash-linked stress audit. Expiry-only reclamation can still expose a healthy incumbent after missed renewal. The evidence supports incumbent-preserving admission when effects are completely mediated, task ownership is authenticated, and lease expiry reflects incumbent liveness.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 16 of its 22 references that are in the map. First posted on arXiv 21 Sep 2026.
Builds on
16 of 22 references.
Closest ancestors · 8
Same direction, newest first
- 2026Reason Less, Verify More: Deterministic Gates Recover a Silent Policy-Violation Failure Mode in Tool-Using LLM Agents8 Jul
- 2026VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills25 Jun
- 2026AgenticOS: An Intent-Oriented Secure Operating System Architecture for Autonomous AI Agents19 Jun
- 2026Sovereign Execution Broker: Enforcing Certificate-Bound Authority in Agentic Control Planes18 Jun
- 2026Alignment Contracts for Agentic Security Systems30 Apr
- 2026The Verifier Tax: Horizon Dependent Safety Success Tradeoffs in Tool Using LLM Agents18 Mar
- 2025Progent: Securing AI Agents with Privilege Control16 Apr
- 2025AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents24 Mar
Other references · 8
- 2025Qwen3 Technical Reportcited by 8,820
- 2026Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflowscited by 30
- 2026AgentCgroup: Understanding and Controlling OS Resources of AI Agentscited by 13
- 2026Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agentscited by 10
- 2026Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systemscited by 8
- 2026Beyond OAuth: Task-Scoped Authorization for AI Agents via Natural Language Slicescited by 5
- 2026Agentic Workflows for Resolving Conflict Over Shared Resources: A Power Grid Applicationcited by 1
- 2026ClashBench: Conflicts Leading Agents to Seize and Harmcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization
- 2026SecureClaw: Clawing Back Control of LLM Agents
- 2025Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
- 2026Harness-MU: A Safe, Governed, and Effective Harness for Multi-User LLM Agents
- 2025MiniScope: A Least Privilege Framework for Authorizing Tool Calling Agents
- 2026The Stochastic Deputy: Structural Tenant Isolation for Tool-Using LLM Agents
- 2026Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races
- 2026Securing LLM Agents Need Intent-to-Execution Integrity