Bistable by Construction: Wall-Clock-Calibrated State Monitors Have No Moment-Detection Regime at Agent Cadence

arXiv:2606.19386 · cs.SE, cs.AI, cs.LG · Submitted 2026-06-15 · Read on arXiv

cs.SE, cs.AI, cs.LG

Submitted: 2026-06-15

Updated: 2026-10-09

Terminology

• Calibration — 1× in this paper · explained in 7 episodes
• Hysteresis — 1× in this paper · explained in 3 episodes

Sources

• AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
• The Saturation Trap and the Subjectivity of Intervention Timing: Why Affect-Based Triggers and LLM Judges Fail to Time Interventions on Autonomous Agents
• ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction
• AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents
• Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties