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

• URL: http://arxiv.org/abs/2606.19386v1
• Date: Mon, 15 Jun 2026 21:25:52 GMT
• Title: Bistable by Construction: Wall-Clock-Calibrated State Monitors Have No Moment-Detection Regime at Agent Cadence
• Abstract summary: We report a State Saturation Trap: threshold-on-state triggers over a continuous affect engine become near-constant alarms on SWE-bench agents.<n>We correct the record (erratum, v2) and treat the flaw as an experiment.<n>We conclude that wall-clock-calibrated leaky-integrator monitors admit no regime in which they act as moment detectors on agent streams.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Runtime monitors for autonomous agents commonly threshold an accumulated internal state - a behavioural baseline, a drift statistic, or, in our prior work, a modelled affective state. We previously reported a State Saturation Trap: threshold-on-state triggers over a continuous affect engine become near-constant alarms on SWE-bench debugging agents (Modgil 2026). A post-release audit found the engine received dt=0 between actions, so its exponential decay never operated: the published trap is a pure-accumulator result. We correct the record (erratum, v2) and treat the flaw as an experiment. The key variable it exposes is whether a monitor's dynamics are calibrated in sample time (per observation, as in CUSUM) or wall-clock time (half-lives in seconds, as in affect models and EMA baselines). On fixed-rate streams these coincide; on agent streams, where inter-action time varies by orders of magnitude, they do not. A pre-registered sweep over uniform intervals (dt in {0..600}s) on 20 trajectories shows the wall-clock level trigger has two regimes: at dt<=1s a constant alarm (20/20; median 18 firings); at dt>=60s silent. Every critical dt lies in (1,30]s. Real agent runs measure latency at median 1.53s (p90 2.33s); real coding cadence sits inside the trap regime, vindicating the empirical finding under a corrected mechanism. The structure is a property of the calibration class, not the engine: a minimal wall-clock accumulator over the raw error stream reproduces the same cliff, while a sample-time CUSUM over the identical stream is exactly dt-invariant (20/20). A rising-edge trigger with hysteresis fires 0-3 times per trajectory in every condition. We conclude that wall-clock-calibrated leaky-integrator monitors admit no regime in which they act as moment detectors on agent streams; transition detection escapes the trap at every cadence, but does not recover human intervention timing.

Related papers

• When the Martingale Never Stops Firing: Anytime-Valid Gating on Real Forecast Streams [0.614481021961242]
  Anytime-valid inference promises evidence that can be acted on at any moment.<n>A deployment inherits it only if the stream it monitors behaves exchangeably.
  arXiv  Detail & Related papers  (2026-08-31T09:32:11Z)
• What the Detector Can See: Evaluating CPS Anomaly Detectors Independently of the Decision Rule [6.145872664954402]
  Anomaly detectors are often the last line of defense for cyber-physical systems.<n>These detectors are usually compared using precision, recall, or F1 at a single operating point.<n>We treat a CPS anomaly detector as a two-stage pipeline: Stage 1 maps observations to residuals, and Stage 2 maps residuals to alarms.<n>We evaluate five detectors across three CPS benchmarks: SWaT, WADI, and HAI.
  arXiv  Detail & Related papers  (2026-08-03T19:35:00Z)
• Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations [59.34593956287438]
  Aionoscope is a diagnostic tool for inspecting latent-state accessibility in frozen time-series representations.<n>Aionoscope separates process generation from observation rendering, producing seeded synthetic streams with exact categorical and dense labels.
  arXiv  Detail & Related papers  (2026-07-01T13:54:20Z)
• A Conditional Timing Protection Level: Holdover-Limited Undetected Time Error Under GNSS Spoofing [0.0]
  A timing receiver under spoofing has no nominal-geometry fault for position-domain RAIM to bound.<n>We show a recorded over-the-air spoof from the public JammerTest 2024 campaign pulled a u-blox ZED-F9P by about 1.01 ms of served time.
  arXiv  Detail & Related papers  (2026-06-23T06:52:58Z)
• When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents [0.0]
  Long-answer LLM agents can fail quietly: they settle on one reading of the evidence early, then spend the rest of the run defending it.<n>We define representational commitment as cross-run hidden-state convergence at a fixed reasoning step.<n>A runtime monitor detects inconsistent trajectories from hidden states at AUROC up to 0.97 (0.85--0.88 under a stricter split)
  arXiv  Detail & Related papers  (2026-06-22T07:13:13Z)
• CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs [100.38986535324284]
  We introduce textbfCIAware-Bench, a benchmark for measuring textbfcontrol textbfintervention (CI) awareness across frontier models.<n>CIAware-Bench tests whether models can distinguish their own trajectories from those modified by a control intervention.
  arXiv  Detail & Related papers  (2026-06-09T16:24:16Z)
• The Distributed Detectability Band Against Marginal-Preserving Attacks [0.0]
  AI-control monitors score individual agent actions to detect misbehavior.<n>Real harm can be distributed across many benign-looking steps, each individually below any per-step alarm.<n>We construct a marginal-preserving, correlation-encoded distributed-sabotage attack.
  arXiv  Detail & Related papers  (2026-06-09T06:04:30Z)
• How VLAs Fail Differently: Black-Box Action Monitoring Reveals Architecture-Specific Failure Signatures [0.0]
  We find that VLA architectures fail in fundamentally different, predictable ways at the motor-command level.<n>We quantify consequence of the well-known discrete/continuous VLA distinction: the two families produce qualitatively different failure monitor works.
  arXiv  Detail & Related papers  (2026-05-27T16:44:55Z)
• TIE: Time Interval Encoding for Video Generation over Events [50.66585165263848]
  Director-style prompting, robotic action prediction, and interactive video agents demand temporal grounding over concurrent events.<n>Modern video generators represent time as discrete points through point-wise positional encodings.<n>Time Interval TIE is a principled, plug-and-play interval-aware generalization.
  arXiv  Detail & Related papers  (2026-05-11T13:23:14Z)
• TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering [70.99933391739154]
  We focus on two recurring failure modes where the agent repeatedly reasons over information it already has, and where it issues tool calls without integrating recent observations or acquiring new evidence.<n>In this paper, we introduce TACT (Think-Act via activation Steering), to detect and mitigate agent drift in the residual stream before it surfaces as a behavioral failure.<n>In specific, we label trajectory steps as overthinking, overacting, or calibrated, and find that their hidden states can separate linearly along two *drift axes*, pointing from calibrated behavior toward each failure mode.
  arXiv  Detail & Related papers  (2026-05-07T10:24:27Z)
• When Your Model Stops Working: Anytime-Valid Calibration Monitoring [0.0]
  PITMonitor is an anytime-valid calibration-specific monitor that detects distributional shifts in probability integral transforms.<n>On river's FriedmanDrift benchmark, PITMonitor detection rates achieves competitive with the strongest baselines.
  arXiv  Detail & Related papers  (2026-03-13T16:50:14Z)
• The Boiling Frog Threshold: Criticality and Blindness in World Model-Based Anomaly Detection Under Gradual Drift [0.0]
  We study world model-based self-monitoring under continuous observation drift across four MuJoCo environments.<n>We find that a sharp detection threshold $varepsilon*$ exists universally.<n>Our results reframe $varepsilon*$ from an emergent world model property to a three-way interaction between noise floor, detector, and environment dynamics.
  arXiv  Detail & Related papers  (2026-03-09T14:51:53Z)
• Forecasting Particle Accelerator Interruptions Using Logistic LASSO Regression [62.997667081978825]
  Unforeseen particle accelerator interruptions, also known as interlocks, lead to abrupt operational changes despite being necessary safety measures. We propose a simple yet powerful binary classification model aiming to forecast such interruptions. The model is formulated as logistic regression penalized by at least absolute shrinkage and selection operator.
  arXiv  Detail & Related papers  (2023-03-15T23:11:30Z)
• Tracking the risk of a deployed model and detecting harmful distribution shifts [105.27463615756733]
  In practice, it may make sense to ignore benign shifts, under which the performance of a deployed model does not degrade substantially. We argue that a sensible method for firing off a warning has to both (a) detect harmful shifts while ignoring benign ones, and (b) allow continuous monitoring of model performance without increasing the false alarm rate.
  arXiv  Detail & Related papers  (2021-10-12T17:21:41Z)
• Detecting Rewards Deterioration in Episodic Reinforcement Learning [63.49923393311052]
  In many RL applications, once training ends, it is vital to detect any deterioration in the agent performance as soon as possible. We consider an episodic framework, where the rewards within each episode are not independent, nor identically-distributed, nor Markov. We define the mean-shift in a way corresponding to deterioration of a temporal signal (such as the rewards), and derive a test for this problem with optimal statistical power.
  arXiv  Detail & Related papers  (2020-10-22T12:45:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.