Adaptive Active Learning for Online Reliability Prediction of Satellite Electronics

Long-horizon LLM multi-agent systems face reliability risks invisible to infrastructure monitoring. We propose the ADE Predictive Reliability Framework (ADE-PRF), enabling proactive health trajectory prediction from passive degradation detection. ADE-PRF aggregates 20 heterogeneous signals across five layers into a Trust Margin (TM) metric (39.2-point dynamic range). Triple-method parallel prediction enables 8-hour forecasts: the Exponential method achieves MAE=1.228, Direction Accuracy=76.8%, with 99.65% within +/-10-point tolerance. Production validation spans 380,227 predictions and 280,579 validations across six agent profiles over 15 continuous days, plus seven sandbox-controlled experiments. Key findings include detection of "false prosperity" -- degradation concealed by normal surface metrics -- and immediate TM coupling with ground-truth states upon ADE plugin integration, with 16/20 factors relying on ADE-collected data. Exponential consistently outperforms Kalman. ADE-PRF provides among the earliest reliability quantification with forward-looking warnings for production LLM agents.

Data-driven remaining useful life (RUL) prediction requires complete degradation trajectories for training, yet such run-to-failure data are scarce and expensive. Practitioners currently lack principled guidance on how many failure examples suffice for a given model and accuracy target. This paper develops a sample complexity framework for RUL prediction comprising seven main results organised around three themes. First, we establish fundamental learning rates: a distribution-free generalization bound shows that the uniform deviation of the mean squared error decreases as $O(B^{2}\sqrt{p/n})$, where $p$ is the model complexity and $n$ the number of trajectories, and a minimax lower bound proves that the $Θ(p/n)$ rate is unimprovable.} \rev{Second, we quantify how domain knowledge accelerates learning: incorporating degradation physics reduces data requirements by up to two orders of magnitude for deep networks, a Bernstein-type analysis achieves the minimax-optimal $O(p/n)$ rate under high signal-to-noise conditions, and closed-form penalties reveal when an incorrectly assumed physics model hurts rather than helps. Third, we characterise the impact of data quality: fleet variability induces an irreducible bias$-$variance tradeoff, while right-censored observations suffer an efficiency loss that depends critically on the degradation class.} Closed-form expressions are provided for exponential, power-law, and stretched-exponential degradation. \rev{Cross-domain validation against published turbofan, battery, and bearing benchmarks confirms the theoretical predictions within a factor of 2$-$3 on average. The results yield practical guidelines for planning data collection, selecting model complexity, and evaluating physics model assumptions in prognostics applications.

We present a Safe Active Learning (SAL) framework for autonomous reliability characterization of rectifying Ga$_2$O$_3$-based devices under coupled thermal and hydrogen stress. SAL treats rectification as a device-physics-motivated safety observable and models its evolution over elapsed time, temperature, and H$_2$ concentration using a Gaussian-process surrogate. To handle condition-dependent and uncertain experiment durations, the method combines an adaptive completion-time window, time-window lower-confidence-bound safety checks, a trust region anchored to previously verified safe conditions, and a two-phase strategy that transitions from conservative safe exploration to progressively relaxed rectification targets as the device degrades. We first evaluate SAL in simulation, where it safely expands the explored region while learning the evolving rectification surface. We then demonstrate SAL experimentally on an automated high-temperature probe-station platform using a Pt/Cr$_2$O$_3$:Mg/$β$-Ga$_2$O$_3$ device. In the reported campaign, phase 1 incurred only one unsafe measurement associated with spurious current-voltage sweeps, while phase 2 intentionally probed lower-rectification regimes. Finally, we use the curated SAL dataset for offline long-horizon forecasting of device response at a target voltage using a structured Gaussian-process model with a condition-dependent Kohlrausch--Williams--Watts mean and a residual covariance kernel. The model captures long-time, saturating degradation trends in an auxiliary validation dataset, illustrating how safety-aware autonomous experimentation enables both conservative characterization and subsequent degradation modeling. Although demonstrated here for a rectifying Ga$_2$O$_3$ device, SAL is applicable to other systems where a measurable in situ safety observable can be defined.