Industrial sensor diagnostics relies on preprocessing, representation, and classification pipelines, making automated pipeline search useful for reducing manual design cost. However, existing automated machine/deep learning (AutoML/AutoDL) reports typically retain only fitted trials, scores, and winners, omitting generated candidates that are invalid, pruned, skipped, cached, or unfitted. This omission limits reviewers'ability to check signal constraints, budget use, and unevaluated legal alternatives. To address this, we propose candidate-fate accounting, a candidate-level audit framework for diagnostic search traces. It records each observed candidate as auditable evidence: hashes merge repeated observations, legality checks flag invalid candidates, allocation rationales explain budget decisions, and a closed fate ledger assigns one terminal fate to each candidate. Experiments on three bearing-diagnostic datasets show that the framework detects invalid candidates and identifies 30--41 candidates omitted by fitted-trial-only reports, with closed fate records verifying complete candidate accounting while maintaining competitive diagnostic performance. The code is available at https://github.com/XXIE999/candidate-fate-accounting.
Data-driven decision pipelines combining predictive machine learning models with downstream optimization software are increasingly used to make high-stakes operational decisions. Certifying the safety, fairness, and reliability of these decisions is essential, yet traditional scenario generation methods rely on repeated random testing, which becomes computationally prohibitive when failure events are rare and offers little insight into why failures occur. We present a framework for local violation certification designed specifically for linear decision pipelines under input uncertainty. We mathematically demonstrate that standard sampling methods fail efficiently for rare violations, motivating a direct structural approach. By analyzing the fixed decision boundary of a deployed pipeline, we show that the local risk of failure can be calculated directly in closed form using a single optimization solve. Furthermore, we introduce an exact sampling procedure and closed-form risk statistics that provide feature-level attributions (identifying which input characteristics contribute most to potential non-compliance) without requiring repetitive random trials or complex sampling algorithms. We demonstrate our approach on an economic power dispatch system subject to emissions regulations, delivering precise, auditable risk assessments at a fraction of the traditional computational cost.
Frozen pretrained forecasters often fail in structured, recurring ways that are costly to repair through fine-tuning. We study corrective feature discovery: mining interpretable features of a frozen forecaster's residual to drive a lightweight post-hoc corrector. Prior automated feature engineering models the data-generating process; corrective features instead model the model-failure process. We present CRAFTER (Corrective Residual Agent with Feature-based Temporal Exploration and Reasoning), which keeps the backbone frozen and mines its residual with two complementary generators: a compositional search over the raw input channels, and a large language model (LLM) that proposes named feature combinations, binary flags, and short executable code. A single validation-grounded gate accepts or rejects every candidate regardless of its origin, and a validation-selected corrector applies the accepted features or leaves the forecast unchanged. This source-agnostic pipeline also allows prior feature-engineering systems to be evaluated under identical conditions, making CRAFTER an instrument for attributing forecast improvements to the feature source alone. Across six public datasets and six frozen backbones, CRAFTER surpasses every dedicated feature-engineering system at every feature budget, roughly doubling the improvement achieved by the corrector alone and reducing the error of the weakest backbones by up to 27%. These gains are robust across different LLM backends and persist even when applied on top of fine-tuned backbones.
Fangxin Wang, Ziyi Zhang, Diyi Zhuang et al.· 0 citations
Autonomous laboratories automate experimental execution, but a campaign must also decide which recovery pathway merits optimization. We formulate this as a sequential decision problem with a discrete pathway-identification stage and a continuous within-pathway optimization stage under heterogeneous experimental costs. Our implementation, Coactive learning, combines a cost-sensitive Bayesian hypothesis-discrimination policy motivated by EC2 (Golovin et al., 2010) with Gaussian-process Bayesian optimization (Srinivas et al., 2010). Under explicitly stated assumptions, the expected spend of one fixed-budget campaign attempt is bounded by the expected pathway-identification cost plus the capped within-pathway optimization budget. We evaluate the method on synthetic benchmarks constrained by selected results reported for PNNL's CICERO selective-precipitation study (Ritchhart et al., 2026). The method performs comparably to an oracle-pathway Bayesian-optimization reference and to a strong split-plate baseline that discriminates pathways with its first plate, without receiving an oracle label for the correct pathway. It is given a candidate hypothesis space and a diagnostic likelihood model. On an NdFeB-inspired instance, it avoids the simulated penalty of a commit-first baseline that initially selects a plausible but inferior hydroxide pathway. This hypothetical wrong-first-commitment scenario is motivated by the hydroxide-oxalate performance contrast reported by CICERO. We characterize the sensitivity of these conclusions to the assumed cost model. The code and benchmark are open source.
Automated visual inspection is a cornerstone of modern manufacturing quality assurance, yet the effectiveness of any detection system is fundamentally bounded by the informativeness of the observations it receives. Most vision–language model (VLM) and reinforcement learning methods for industrial defect detection assume a fixed set of observations and optimize only the reasoning applied to them. We introduce ActiveInspect, which formulates inspection as budget-constrained sequential selection of multi-view, multi-modal evidence. Starting from a pre-acquired observation pool, a single policy selects an additional view or modality, zooms into a candidate region, retrieves a matched normal reference, or terminates with a verdict. The policy is initialized by perception-activated supervised fine-tuning (PA-SFT) and subsequently optimized by group relative policy optimization (GRPO) using inspection-specific rewards. Depth and point-cloud measurements are converted into VLM-compatible geometric renderings, while a structured memory integrates evidence across inspection steps. Evaluation on Real-IAD D3, Real-IAD, MVTec 3D-AD, MVTec-AD, VisA, and MMAD demonstrates a consistent improvement in the accuracy–observation trade-off. On Real-IAD D3, ActiveInspect increases image-level area under the receiver operating characteristic curve (I-AUROC) from 0.890 to 0.906 (mean over three training seeds; p<0.01) relative to the passive D3M baseline while reducing the average observation count from 3.0 to 2.7. It reaches 99.8% of the I-AUROC obtained by exhaustive evaluation of all 15 observations while using 18% of that observation count, and it reduces per-sample inference time by a factor of 5.3 relative to the exhaustive scan. The largest gains occur for geometry-dependent defects, including dents, warping, and concavities.
Jingyuan Wang, Ming Wu· Italian National Conference...· 0 citations
Automated anomaly detection methods often report strong performance on curated academic benchmarks, but their behavior under real-world industrial conditions is less clear. In this work, we evaluate 19 unsupervised anomaly detection models on the BowTie dataset, a challenging manufacturing dataset with reflective surfaces, subtle defects, and profile-specific variation. In contrast to benchmark results, we observe that model performance is less stable than typically reported on standard benchmarks such as MVTec AD, highly sensitive to preprocessing, and inconsistent across conditions, with no single approach emerging as uniformly robust; a consensus audit further indicates that nominal-data quality affects deployment. Motivated by these findings, we developed and initially deployed a unified human-in-the-loop framework for manufactured-part inspection that combines image annotation, AI-assisted defect detection, and an integrated validation engine, replacing a prior manual visual inspection and documentation workflow. The system supports heatmap-guided defect review, SAM-refined candidate regions for inspector acceptance, rejection, or boundary adjustment, mask evaluation where annotations exist, and review history for inspector consistency and onboarding. Together, the results highlight the gap between benchmark performance and deployment reality, and provide a practical framework for addressing it.
Mike Szklarzewski, CJ George, Gavin Smithson et al.· 0 citations
Reliable evaluation of tool routing is critical as Large Language Models increasingly operate as autonomous agents. Current benchmarks face three structural limitations: data distributions that follow a power law leave rare scenarios underrepresented; the absence of adversarial hard negatives obscures performance differences across models; and annotation pipelines depend on LLM judgments that have not been validated through execution. In this paper, we introduce PluginEval, a benchmark constructed through a two-stage framework that systematically mitigates these limitations. First, we formulate tool routing as a sequence of three decisions and separate generation from verification. LLMs propose candidate calls, while deterministic validation and real API execution provide reliable quality signals. Second, we decompose each plugin by capability, intent, and boundary to identify trigger and exclusion scenarios. We then generate queries at different difficulty levels to fill coverage gaps, including adversarial negatives targeting three failure modes, and return them to the first stage for annotation. This process creates a closed loop that iterates until coverage converges. For evaluation, we move beyond aggregate accuracy. An LLM judge anchored to gold annotations classifies failures as missed calls, spurious calls, or parameter errors, producing a detailed error profile for each model. We evaluate five model families, including proprietary models and models with open weights, analyze their performance across difficulty levels and error categories, and validate the judge through agreement with human annotations.
