Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races

arXiv:2609.29522 · cs.AI · Submitted 2026-08-25 · Read on arXiv

cs.AI

Submitted: 2026-08-25

Updated: 2026-08-25

Terminology

• Verification — 21× in this paper · explained in 2 episodes
• Abstention — 9× in this paper · explained in 1 episode
• AUROC — 6× in this paper · explained in 2 episodes
• Benchmark — 5× in this paper · explained in 2 episodes
• Calibration — 4× in this paper · explained in 7 episodes
• Verifier — 4× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 4 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Actor — 1× in this paper · explained in 3 episodes
• Agentic Workflows — 1× in this paper · explained in 1 episode
• LLM judge — 1× in this paper · explained in 2 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Regret — 1× in this paper · explained in 3 episodes

Sources

• When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents
• STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
• STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics
• ToolGate: Contract-Grounded and Verified Tool Execution for LLMs
• Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows
• Verified Tool Calls Improve LLM Agent Reliability Under Non-Atomic Failures
• The Verifier Tax: Horizon Dependent Safety Success Tradeoffs in Tool Using LLM Agents
• Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents
• S-Bus: Automatic Read-Set Reconstruction for Multi-Agent LLM State Coordination
• What Can Be Enforced? A Theory of Certified Runtime Safety for Tool-Using Agents
• Mind the Gap: Time-of-Check to Time-of-Use Vulnerabilities in LLM-Enabled Agents
• Agentic Confidence Calibration
• AgentAbstain: Do LLM Agents Know When Not to Act?
• Agentic Abstention: Do Agents Know When to Stop Instead of Act?
• Safe, Untrusted, "Proof-Carrying" AI Agents: toward the agentic lakehouse
• Agent-Diff: Benchmarking LLM Agents on Enterprise API Tasks via Code Execution with State-Diff-Based Evaluation

Related papers

• 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
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection