Reliable

Auto-research agents, LLM systems that propose, implement, train, and evaluate model changes across iterations, promise to automate applied ML's experimental loop. Over long horizons, execution accuracy is a binding constraint: a change can silently leak held-out data, omit normalization, disconnect a gradient, or leave a train/eval flag unwired, invalidating expensive runs and compounding error across iterations. We present RankEvolve, an auto-research framework for evolving generative ranking models. An Executable Operating Protocol (EOP) declares phases, gates, branches, and loops, and the runtime enforces the compiled state machine. A meta-meta-harness composes complete black-box coding-agent products, including Claude Code and Codex, as execution-graph nodes that review and repair one another's work. In a budget-matched evaluation, heterogeneous composition raises all-oracle execution accuracy from the best single-product baseline of 45.8 percent to 62.5 percent (paired +16.7 points, 95 percent CI [6.6, 26.7]) while achieving a 10.4 percent silent critical-defect rate. An implemented knowledge layer carries findings, including negative results, across iterations. In a twelve-iteration deployment on the open-source HSTU recommender, RankEvolve reported NDCG@10 of 0.2192 on MovieLens-20M LARGE (+4.48 percent over the published anchor) and 0.1948 on BASE (+2.80 percent). ExecML-HSTU, seeded by incidents from that deployment, provides the oracle benchmark for the execution-accuracy evaluation. A pre-specified LitGPT transfer split replicates the heterogeneous-composition effect beyond recommendation (+12.5 points, 95 percent CI [3.0, 22.0]), and a paired ablation isolates per-step from full-protocol instruction injection. These results characterize when runtime-controlled composition of coding-agent products improves execution accuracy.

GUI agents built on large language and vision-language models still struggle on unseen applications and complex multi-step tasks, as completing real GUI tasks depends on app-specific, temporally volatile operational knowledge that is scarce in pretraining corpora. Retrieval-augmented execution offers a natural remedy but faces two coupled bottlenecks: knowledge at scale is hard to acquire, and self-collected priors inevitably drift from the live environment due to version updates, promotions, ads, A/B tests, and personalization. We therefore argue that GUI agents should not pursue perfect knowledge but learn to act correctly under imperfect priors, and propose our framework that couples knowledge acquisition with noise-robust utilization: a structured exploration strategy traverses interactive elements, builds a UI state-transition graph, and synthesizes (task, trajectory) pairs via a VLM without human annotation; a noise-aware training strategy, grounded in a taxonomy of real GUI drift patterns, injects five types of realistic errors into self-explored trajectories to teach the agent to assess prior reliability before acting. Experiments on physical devices and online emulator benchmarks show that our method discovers more unique screens, covers more benchmark tasks, and more effectively rejects erroneous priors while leveraging correct ones, with accuracy gains that transfer across datasets.

We investigate whether predicted Mean Opinion Scores (MOS) can reliably support system-level comparisons of speech enhancement (SE) methods by introducing system-level preference accuracy (SPA). Although MOS prediction models are widely used to evaluate SE systems, their performance is typically assessed by correlation with human-rated MOS, which does not guarantee agreement on which system is better. SPA addresses this gap by directly evaluating whether predicted and human-rated MOS yield the same system preferences. Using SPA, we systematically evaluate three settings: single prediction models, ensembling, and domain adaptation. Through experiments, SPA varies substantially across single prediction models, from 9.4% to 76.8%. Even the best model disagrees with human judgments in approximately 23% of system comparisons. Ensembling yields only limited improvement, while domain adaptation tends to substantially improve SPA in the closed condition but brings only modest gains in the more practical open condition, where neither the target systems nor the speakers are known. These results suggest that SPA can reveal errors correlation-based evaluation alone does not expose, and that predicted MOS alone can lead to unreliable conclusions in practical SE system comparison.

Reliable embodied decisions under partial observability require informative observations and sufficient supporting evidence. However, semantic scores alone do not reveal which viewpoints justify a claim or where additional evidence should be acquired. We introduce SafeVantage, a vantage-aware semantic memory and active acquisition framework that retains each claim's supporting views, camera poses, and estimated target location, keeping positive support distinct from search coverage. A learned candidate-observability model uses claim-grounded geometry to predict target visibility at reachable viewpoints. These predictions guide view selection through expected reduction in terminal decision loss, accounting for travel cost and geometrically distinct corroboration. A calibrated head then combines support, spatial consistency, and coverage to produce Yes, No, or Abstain decisions. We evaluate SafeVantage on a category-presence benchmark spanning 232 unseen ProcTHOR houses and 7,424 paired episodes per method and action budget. Compared with validation-selected equal-budget baselines, SafeVantage achieves macro-F1 gains of 24.7% and 12.0% at eight and twelve actions, respectively, with lower risk and higher answer rates at both budgets and 31.7% less travel at eight actions. Equal-input HM3D experiments show lower selective risk under fixed observations, while controlled ScanNet interventions show that restoring supporting views improves downstream VLM answers. Ablations further support the contribution of candidate observability to decision quality and acquisition efficiency. Results demonstrate the value of claim-level viewpoint evidence for connecting semantic memory, active acquisition, and reliable decision-making. Code is available at https://safevantage.github.io

AI reliability concerns whether an AI system performs its intended function dependably over a stated period and under stated operating conditions, with stated evidence. As these systems become more autonomous, that function includes more than a correct output. Retrieval, memory, tool use, permissions, human oversight, and interactions among systems must operate consistently and safely, and, for generative systems, so must the reasoning process that produces the output. Average benchmark accuracy measures capability; it does not quantify this broader reliability claim. This paper adapts established reliability engineering methods, from failure definitions and operational envelopes to FMEA, accelerated testing, field monitoring, and reliability growth, to AI systems. A four-level diagnostic framework classifies failures as component, operational-loop, agentic-conduct, or network and governance failures. Test, evaluation, verification, and validation (TEVV), sequential monitoring, and FRACAS create and refresh evidence. SMART provides statistical guidance for measurement, analysis, assessment, and test planning; the NIST AI Risk Management Framework provides organizational guidance for governance, evaluation, monitoring, and mitigation. Three cases illustrate the program: adversarial testing of a convolutional neural network, perception-error propagation, and autonomous-vehicle disengagements. Established reliability engineering provides a usable foundation; new measurements and safety guardrails are still needed as these systems are self-evolving.

Vision-Language-Action (VLA) models for autonomous driving rely heavily on successful expert demonstrations, leaving model-specific failures underexploited. Learning from these failures is hindered by unreliable diagnoses, poorly matched correction targets, and coarse rewards. We propose RefineDrive, a failure-guided post-training framework that learns from self-generated failures through targeted supervision and safety-aware reinforcement learning. Reliable Diagnosis derives structured, verifiable feedback on collisions and drivable-area violations directly from simulator states. Minimum-Correction Target Retrieval searches a clustered human trajectory bank for nearby corrections that satisfy hard-safety constraints in the current scene, prioritizing preservation of the failed prediction's motion pattern. Conditioned on the driving context and failed trajectory, Correction SFT learns to generate the diagnosis followed by the retrieved correction as a training-only auxiliary task. We then apply GRPO with a Safety-Layered Reward that strictly prioritizes hard-safe trajectories, retains continuous safety feedback for both unsafe and hard-safe trajectories, and rewards driving progress only after hard safety is satisfied. At inference, the policy directly predicts trajectories from the driving context without an explicit diagnosis or repair stage. On NAVSIM v1, RefineDrive improves the 4B base SFT policy from 87.7 to 91.7 PDMS. Using the same checkpoint without additional training, RefineDrive achieves 89.4 EPDMS on the original NAVTEST scenes evaluated with NAVSIM v2 extended metrics. Controlled ablations support the benefits of structured diagnosis supervision, retrieved corrections, and safety-layered optimization for direct planning.

Task-oriented dialogue requires maintaining and updating information across turns, yet language models expose no explicit belief-state object. We study how conversational state is represented, updated, and used inside eight instruction-tuned language models from four families on MultiWOZ and SGD. Structure and values separate: which domains, slots, and requests are active is linearly readable just before the model acts, whereas exact values are far more readable where the user stated them. After a user changes a value, both values remain accessible at their mentions, and causal interventions show that both continue to influence the model's action. In natural closed-loop interaction, query failures separate into cases of weak structural support, incorrect value resolution, and failure to deploy otherwise-supported constraints, with targeted interventions producing systematically different repair behavior across these cases. These findings motivate a state-action controller that starts from the base model action and selectively edits it using structural readouts, without requiring a complete predicted belief state as an intermediate representation. On held-out MultiWOZ interaction across five models, it raises the base model exact-query accuracy from .318 to .621 and task success from .272 to .371 at negligible added cost. Overall, reliable interaction requires not only retaining conversational information, but resolving which available constraints currently apply and ensuring that they govern action.

Reliability theory gives a mature language for layered systems, but its formal tools are not yet standard in frontier AI control. We apply them to Google DeepMind's defenses against rogue deployment. The same control stack can have cubic, quadratic, or linear rare-failure suppression depending on its failure domains. Birnbaum importance identifies which component improvements buy the most nominal reliability, while prevention changes the population on which recovery is demanded. These results give concrete guidance about what to separate, improve, measure, and test.

Low-resource text-to-speech (TTS) adaptation is constrained by scarce paired data and costly manual transcription. Existing fixed-voice TTS systems can provide relatively accurate pronunciation, but their synthetic speech offers limited speaker diversity and may exhibit flat prosody. Real recordings provide natural prosody and diverse voices, yet their automatic speech recognition (ASR) pseudo-labels may contain transcription errors. We find that supervision order affects content accuracy and speaker similarity. We propose trust-aware progressive adaptation: synthetic-to-real adaptation first establishes text-speech correspondences, then restores reference-speaker control using real speech. Transcript-agreement weighting uses agreement between two fixed ASR systems as a proxy for pseudo-label reliability to limit noisy supervision. Experiments with FireRedTTS3 on Burmese and Lao and OmniVoice on Burmese show improved content accuracy with high naturalness and competitive speaker similarity. Jointly considering supervision order and pseudo-label reliability when combining synthetic and real speech offers a practical path to zero-shot voice cloning in low-resource languages with less manual transcription. Audio demos are available at https://insiderx-pro.github.io/S2R-Adaptation-TTS/

Virtual sensing, the estimation of hard-to-measure quantities from available sensor measurements, is a critical enabler for control and monitoring in cyber-physical systems. However, when sensors fail, learning-based predictors can produce physically implausible estimates that propagate to system-level failures. We argue that real-world deployment demands robustness and introduce MuViS-C, the first multi-domain benchmark of robustness against common sensor failures in learning-based virtual sensing. Building on an existing nominal-performance benchmark and established corruption taxonomies, it covers ten sensor failure modes, from subtle drifts to catastrophic signal dropouts, at multiple severities. These are paired with complementary robustness measures capturing average error under corruption, relative degradation, and worst-case fragility. Across nine datasets from six domains, we benchmark six architectures spanning gradient-boosted trees and the major inductive biases for sequence modeling: convolution, recurrence, attention, and MLP-mixing. On the attention-based architecture, we further probe three robustification strategies. We find that (i) every model degrades substantially under corruption, becoming worse than a naïve predictor on at least one corruption setting, (ii) gradient-boosted tree ensembles achieve strong robustness, and (iii) dedicated robustification closes the gap between the attention-based architecture and the most robust models, though each strategy hurts nominal performance. The benchmark's multi-domain design proves essential, as model rankings shift across datasets, and no single domain captures the full robustness picture. MuViS-C is open-source and extensible to new datasets, failure modes, measures, and models.

Vision-Language Models (VLMs) are increasingly used to evaluate robot manipulation outcomes, but existing benchmarks offer limited evidence of cross-domain generalization. We introduce FailBench, a benchmark for robot failure detection comprising 2,197 manipulation attempts across 14 public sources (12 real-world, 2 simulated). In FailBench, 75% of failures occur naturally, and six real-world sources come from non-failure-detection datasets. Evaluating 13 VLM-based detectors, we find the best model achieves only 0.77 mean balanced accuracy. Notably, models fine-tuned for failure detection consistently underperform general-purpose VLMs and their own pretrained baselines. Performance depends heavily on required visual evidence: models approach saturation when outcomes depend on observable object motion, but degrade to near-chance (<0.60 balanced accuracy) on contact-intensive assembly tasks. Error analysis reveals a systematic bias toward predicting success under ambiguous evidence, which persists even with increased reasoning effort. Finally, we show that input-level intervention--spatially localizing and cropping outcome-relevant regions--improves the top detector by 2.4 percentage points without extra training.

LLM-based software systems increasingly require effective "evals" as quality gates in the development lifecycle. However, existing work typically addresses individual aspects of eval reliability rather than the full set of practical requirements. We present an end-to-end eval pipeline that combines eval checklist creation, with learned aggregation for checklist responses, to improve agreement across LLM judges and accuracy against human judgments. The framework additionally pro- vides self-consistency, explanations, and prediction uncertainty, and we empirically demonstrate its effectiveness.

Compositional reliability bounds for multi-agent systems multiply component reliabilities, a step licensed by a conditional-independence assumption that is routinely stated and rarely tested. We test it. Two instances of one model, in a two-agent handoff, co-fail on 90.0% of the missions on which either fails (log OR 6.66, 95% CI [6.38, 7.00]; phi 0.916), in a preregistered evaluation of 18,000 missions scored by deterministic code with no LLM judge. Substituting a different model reduces the association in six of six contrasts; substituting a different vendor, model already different, does not -- a registered hypothesis reported as a null. The error is signed and runs against the operator: positive dependence inflates joint failure above the independence product, so redundancy is over-credited exactly when components share a model. The assumption-free alternative is often vacuous, and fitting a dependence model is worse: we prove a bootstrap bound on a fitted model's functional loses coverage of the truth as n grows, the identification gap being O(1) while the bootstrap haircut is O(n^{-1/2}). More data makes such a certificate worse, with no visible symptom. We give a finite-sample certificate assuming no dependence structure: a linear program over the joint, over a Bonferroni-Clopper-Pearson box around measured co-execution moments. It is sound, sharp for the information supplied, and monotone in the moment family. Enriching ten moment functionals to fourteen narrows the identified interval by 85.7% and lifts the certified floor from 0.2455 to 0.4116. A companion anytime-valid certificate holds type-I error at 0.0471 under optional stopping. Common dependence statistics are marginal-bounded and can reverse an apparent ordering of conditions when the compared agents fail at different rates. Contracts, scoring code, analysis scripts, and the preregistration are released.

Recent advances in Large Language Models (LLMs) have demonstrated strong capabilities in generating semantically relevant concepts and relations, making them promising tools for taxonomy enrichment. However, directly relying on LLM-generated expansions often leads to noisy, redundant, or hierarchically inconsistent structures, limiting their reliability for automated taxonomy expansion. In this paper, we present ReLTEx, a framework for reliable LLM-based taxonomy expansion. ReLTEx combines LLM-driven candidate generation with structure-aware validation and recursive expansion control to improve the consistency and quality of generated taxonomies by reducing hallucinations. We evaluate the proposed framework using benchmark taxonomies under a masked taxonomy expansion setting and compare multiple validation strategies. Experimental results, supported by both adapted evaluation metrics and human evaluation, demonstrate that ReLTEx produces more reliable and semantically coherent taxonomy expansions.

Reinforcement Fine-Tuning (RFT) has enabled medical Multimodal Large Language Models (MLLMs) to produce Chain-of-Thought (CoT) reasoning for visual question answering, yet these models suffer from $\textit{confidence miscalibration}$---a systematic gap between expressed certainty and actual diagnostic accuracy that undermines clinical trust. We propose $\textbf{CARE}$, a $\textbf{C}$onfidence-$\textbf{A}$ware medical $\textbf{RE}$asoning framework that jointly optimizes accuracy and calibration through a dual-stage pipeline. First, a scalable Medical-CoT synthesis provides structured cold-start data for Supervised Fine-Tuning. Second, Group Relative Policy Optimization (GRPO) with a novel $\textbf{Confidence-Aware Reward (CAR)}$ mechanism ties the model's confidence to diagnostic correctness within the reward signal. Across three Medical VQA benchmarks, $\textbf{CARE}$ achieves the highest diagnostic accuracy while obtaining the lowest Expected Calibration Error and Hallucination Rate, establishing a foundation for trustworthy clinical decision support. Our code is available at https://github.com/anotherbricki/CARE.

Recent research empowers Large Language Models (LLMs) as multi-turn search agents to iteratively retrieve and generate outputs until complex tasks are solved. However, the contexts of multi-turn search agents are lengthy and complex. For example, the retrieved set of documents in each turn would inevitably introduce irrelevant information that distracts LLMs, referring to \textit{context interference}, potentially hindering the reliability and efficiency of search agents. Therefore, we conduct a systematic study on context interference in multi-turn search agents, focusing on investigating i) which parts of the context of search agents will contribute to the context interference, ii) how to refine the contexts of search agents to mitigate the interference, and iii) can incorporating context refinement into search agent training yield further improvements. We reveal that interference primarily arises from the latest retrieved documents. Based on the explored findings, we then introduce a distill-based context refiner to dynamically mitigate context interference for multi-turn search agents. Finally, we validate that incorporating context refinement into RL training pipelines of search agents can significantly enhance both reliability and efficiency. This study highlights the importance of mitigating context interference of search agents, inspiring a novel paradigm of ``refine context and then generate'' for AI agents.

Building reliable applications that leverage large language models (LLMs) remains a significant challenge. While LLMs offer impressive capabilities across diverse tasks, their outputs often lack accuracy and provide no clear measure of confidence. This uncertainty compounds in flows of multiple calls to LLMs and other tools, making it difficult for developers and end-users to trust the results. This paper introduces a probabilistic language for programming LLM-based flows. It enables developers to quantify and propagate uncertainty throughout the application's flow, and experiment with different inference scaling techniques without adding a single line of code beyond the flow's logic. We present an experimental study to demonstrate this capability, and a case study building a theorem proving agent for the Rocq theorem prover.

The daily allocation of the finite 24-hour time budget is strongly associated with physical, mental, and cognitive health. While predictive models can estimate the relationship between time-use compositions and health outcomes such as body mass index, life satisfaction, and cognition, most optimization approaches focus only on maximizing expected benefit and do not consider the uncertainty inherent in data-driven prediction. Ignoring uncertainty in health-related decisions can lead to unrealistic time-use recommendations. To address this gap, we introduce an uncertainty quantification Quality Diversity (QD) framework for a more reliable time-use recommendation. Objective functions are derived using compositional data analysis using a large child cohort dataset n > 1000, to capture the relationship between daily activity compositions and multiple health indicators. We develop a new approach that incorporates predictive uncertainty into QD processes and produces more reliable recommendations that balance the expected health benefits with the confidence of the model. We explore the solution space through variable-based and objective-based behavioral representations, revealing diverse high-quality time-use composition and explicit relationships between health outcomes under uncertainty. By embedding uncertainty directly into optimization, our framework shifts the time-use recommendations toward regions of lower uncertainty while preserving high-quality structures for more reliable decision-making in behavioral health.

Anomaly detection is a safety-critical machine learning problem with applications ranging from fraud detection to network intrusion prevention and industrial monitoring. Despite the large number of proposed anomaly detection algorithms, many novel methods claim state-of-the-art performance. However, many authors do so under benchmark settings that are not aligned with one another. This lack of comparability raises concerns regarding the reproducibility and reliability of anomaly detection benchmarks. In this work, we study the impact of common benchmarking choices on the stability of algorithm rankings. Using seven representative anomaly detection algorithms and 690 datasets from the OddBench benchmark suite, we analyze how rankings change under varying dataset selections, evaluation metrics, hyperparameter configurations, and random seeds. To quantify this effect, we introduce a rank instability metric measuring the variability of algorithm rankings across benchmark settings. Our results show that algorithm rankings in anomaly detection are highly unstable. In many cases, almost every competitive algorithm can appear as the best-performing method under some benchmark configuration. Among the studied factors, dataset selection and hyperparameter choice contribute most strongly to ranking uncertainty, while random seeds and evaluation metrics have a comparatively limited impact. We also observe that reliable benchmarking requires substantially larger and more diverse dataset collections than the ones commonly used in prior work.

Fetal brain biometry is essential for quantitative assessment of brain development, supporting gestational age estimation, developmental monitoring, and detection of abnormalities. In clinical practice, measurements are manually performed, making them time-consuming and prone to variability. While automated approaches have been proposed, reproducible methods remain limited, particularly those providing anatomically interpretable landmark localization. We present a fully automated deep learning-based framework for reliable and reproducible brain biometry from 3D super-resolution-reconstructed fetal brain MRI. The proposed four-step pipeline derives biometric parameters by jointly estimating linear measurements and their corresponding anatomical landmarks. A 3D convolutional neural network is trained to regress landmark coordinates from brain segmentation label maps, followed by measurement-specific geometric optimization to refine landmark positions and compute measurements. The pipeline is evaluated on two publicly available fetal MRI datasets comprising 150 volumes (gestational age range: 20-37 weeks) acquired across different scanners and protocols, assessing five key biometric measurements across varying acquisition settings and providing a comprehensive evaluation of both measurement accuracy and landmark localization using quantitative metrics and visual assessment. Compared with the only available automated pipeline, the proposed method achieves comparable or improved accuracy for most measurements. In conclusion, we introduce a straightforward pipeline for reliable biometry estimations, with efficiency, interpretability and scalability that support integration into clinical workflows.

Large language models (LLMs) have demonstrated strong capabilities in structured query generation, making them a natural choice for Text-to-SPARQL, which translates natural language questions into executable SPARQL queries over knowledge graphs. However, their initial outputs remain unreliable: generated queries may be executable yet semantically misaligned with input questions, leading to incorrect retrieval. To address this issue, we propose Generator-Gate-Corrector (GGC), a framework for reliable LLM-based Text-to-SPARQL generation. GGC first uses a Generator to produce an initial query, then applies a Gate to predict whether correction is needed, and finally invokes a Corrector only for selected high-risk queries. This selective correction mechanism avoids unnecessary modifications and reduces the risk of degrading originally correct queries. Experiments on MCQA show that GGC improves query-level accuracy from 90.23% to 98.33% while reducing inference overhead by 45% compared with correcting all generated queries. Ablation studies show that the Gate is robust across thresholds and that Corrector training data composition affects correction effectiveness and stability. Overall, the results demonstrate that selective correction enhances the accuracy, reliability, and efficiency of LLM-based text-to-SPARQL generation.

As LLM-based agents are deployed in complex, multi-step workflows, a critical evaluation gap has emerged: most existing benchmarks judge only final outcomes, unable to distinguish reliable reasoning from lucky success or attribute failures to specific process deficiencies, hindering attribution in long-horizon tasks. In this work, we present ClawTrack, a dual-assessment benchmark that simultaneously measures what an agent achieves (Task Score) and how it achieves it (Process Score). ClawTrack comprises 320 tasks across 8 domains with 25+ deterministic mock services. A Process Grader scores each reasoning turn along four dimensions (goal alignment, efficiency, information utilization, and result verification), anchored by 12,541 task-specific rubric items. Evaluating 21 models over 16,000+ trials, we find that: (1) process scores effectively attribute success and failure to specific reasoning dimensions, filtering lucky passes invisible to outcome-only evaluation; (2) the four dimensions are complementary, with result verification as the systematic bottleneck; (3) the framework is robust to evaluator choice across different judge LLMs; and (4) process-based trajectory filtering yields consistent post-training improvements across model scales.

Deep learning has shown strong potential in medical image analysis, but most existing methods rely on large-scale annotations and a closed-world assumption that rarely holds in clinical practice. Although Generalized Category Discovery (GCD) has advanced rapidly on natural images, it remains underexplored in medical imaging. To address this issue, we propose MedXplore, a unified framework for reliable and unbiased medical GCD, optimizing from both perceptual and decision levels. Specifically, at the perceptual level, taking a frequency domain perspective, Frequency-SNR Adaptive Attention and Consistency (FAAC) performs learnable full-spectrum filtering and global-local energy contrast activation to not only highlight local abnormal signals relative to the global context, but also provide reliable semantic anchors for patch consistency learning. At the decision level, Adaptive Cosine-Angular Margin (ACAM) adjusts angular margins using semantic difficulty and feature confidence to balance intra-class compactness and inter-class separability. Together, the two modules improve lesion-sensitive representation learning and mitigate old-class bias. Experiments on multiple benchmarks show an average \textbf{8.5%} gain in \textit{All} accuracy over the strongest competing methods. On Kvasir, MedXplore reduces false-old errors from 14.50% to 0.80%, demonstrating strong robustness under severe old-new ambiguity.

Measuring conversational states such as cognitive load and conversational power from multimodal behavior requires characteristic features that are not only predictive but also reliable across task contexts. We present a three-dimensional evaluation framework assessing predictive accuracy, cross-task generalizability, and test-retest reliability, applied to interactional, acoustic, and linguistic features extracted from dyadic conversations during collaborative tasks performed over a video-conferencing platform (AVCAffe dataset; 53 dyads, 9 tasks). Our results show that no single feature family dominates all three dimensions. Linguistic features show the highest predictive accuracy for cognitive load but collapse under cross-task evaluation, revealing sensitivity to task-specific vocabulary. Additionally, acoustic reliability, often reported as evidence of feature stability, degrades once speaker identity is controlled, confirming that standard prosodic features measure vocal characteristics rather than conversational state. Interaction features provide the only genuinely reliable signal, unchanged after speaker normalization. Interestingly, classifying power role remained near chance baseline across all conditions, indicating limitations of task-level aggregated behavior for predicting power role in conversation. Our findings reveal three insights: (1) linguistic features predict best but generalize poorly across task contexts; (2) acoustic reliability collapses to near-zero once speaker identity is controlled, challenging standard evaluation practice; and (3) interaction features provide the only genuinely reliable signal, with floor dominance predicting within-dyad cognitive load asymmetry. These results argue for speaker normalization and multi-dimensional evaluation as prerequisites for context-aware, robust multimodal feature selection in conversational systems.

Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing. However, LLMs often suffer from hallucinations and lack of relevant knowledge when dealing with question answering (QA) tasks. To mitigate these issues, knowledge graphs (KGs) have been utilized to enhance LLM reasoning. Nevertheless, KGs often contain noise and errors, while existing KG-enhanced LLM approaches are generally unable to identify and filter such noisy and erroneous content, which can instead amplify hallucinations and pose challenges for reliable reasoning. Uncertain knowledge graphs (UKGs), which associate each triple with a confidence score to quantify uncertainty, offer a promising direction to address this challenge. Compared with prior work, we investigate how to leverage UKGs to support LLMs for QA. We propose Debate-on-Graph (DoG), a new framework that enables LLMs and UKGs to collaborate adaptively for reliable reasoning. Specifically, we first design a heuristic search algorithm tailored for UKGs to extract reliable and question-relevant subgraphs, thereby reducing noise and errors in retrieved knowledge. We then introduce a Multi-Agent Debate mechanism, which yields reliable answers through adaptive adversarial debates, aiming to fully exploit the knowledge in UKGs while preserving the reliability of retrieved evidence. Extensive experiments on four benchmark QA datasets show that DoG achieves state-of-the-art performance over existing LLM reasoning methods and KG-based baselines, while enabling reliable and adaptive reasoning. Our code is available at https://github.com/seucoin/Debate-on-Graph.

While Large Language Models (LLMs) have demonstrated significant capability in software code generation, their application to analog Electronic Design Automation (EDA) is bottlenecked. Owing to limited circuit topology understanding and data, directly prompting LLMs and multimodal models leads to hallucinations and failure to produce schematics capable of passing rigorous SPICE simulations, as we show in our work. Instead, we propose an end-to-end, multi-step LLM agentic framework ATLAS, capable of generating a functional Successive Approximation Register (SAR) Analog-to-Digital Converter (ADC) that successfully passes simulation validation. To adhere to the rigid constraints of analog design, we utilize expert knowledge to ground the LLM in its planning, selection, parameterization, and iterative modification. As part of ATLAS, we introduce Template-Constrained Generation - which unlike other template-based works - builds towards a more generalized SAR ADC generation flow. We demonstrate a strong proof-of-concept of our framework by developing SAR ADCs across technology nodes and input specs. Overall, our expert-knowledge grounded multi-step agentic ATLAS establishes a pragmatic foundation for integrating LLMs into reliable analog design methodologies.

Product data scientists often ask LLM-based agents to help with recurring execution tasks such as cleaning data, writing SQL, choosing statistical tests, and formatting results. Reusable skill files are meant to avoid prompting from scratch by packaging guidance for a task family. Expert-written skills can encode high-quality guidance, but writing and maintaining them across many data-science task families creates a manual bottleneck. We ask whether LLM-generated skills offer a useful low-curation alternative: do they improve performance over the task prompt alone? We test this question across four lifecycle stages: data preparation, data extraction, statistical analysis, and reporting, using one generated skill per stage. We find no reliable improvement from full generated skills over No-Skill prompting. We then ask whether any part of the skill is useful by ablating different skill components. The main ablation covers 56 tasks, nine model configurations, and three providers, yielding 7,560 runs. Compared with prompting using the task alone, neither the full generated skill nor any ablated skill variant significantly improves performance; all p-values are at least 0.396, and the total spread across variants is only 1.2 pp. A supplemental token-matched control adds 1,512 runs and finds that Full skills perform similarly to task-irrelevant skill-formatted content. The results caution against using one LLM-generated skill per data-science workflow as a default single-shot prompting strategy.

Data-driven embodied AI is rapidly transitioning into a paradigm that scales training through massively parallel simulation, where GPU-accelerated simulators serve as the foundational data infrastructure. However, as computational throughput scales, the underlying trade-offs between parallel efficiency, physical fidelity, and execution determinism remain largely unexamined, hindering the development of reliable robot learning. In this paper, we expose the hidden limits of mainstream GPU-based robotic simulators (e.g., Isaac Lab, Genesis) by introducing GPUSimBench, which focuses on scalability, physical consistency, and computational determinism. First, GPUSimBench establishes a physical grounding evaluation with a controlled inclined-plane task, quantifying the distributional alignment between simulated dynamics and their real-world counterparts. Second, we benchmark parallel scalability by measuring throughput and memory footprints across scaling environment counts. Crucially, beyond standard performance metrics, we unveil and quantify the inherent non-determinism introduced by GPU-batched execution, characterized by significant run-to-run and inter-environment variability even under identical initial conditions. Finally, we identify four empirical regimes of stochasticity within current simulator stacks, highlighting that unbounded scaling can compromise reproducibility without explicit constraints.

In selective deployment, practitioners act only on a model-chosen subset of individuals based on predicted conditional average treatment effects, but marginal conformal guarantees need not control reliability on that selected subset. We study reliable selection for black-box CATE predictors: selecting candidates whose CATE errors are below a tolerance while controlling the false discovery rate (FDR). Since CATE errors are unobservable, we construct doubly robust proxy errors from pseudo-outcomes; however, naive proxies can lose power under heteroskedasticity because variance overwhelms the reliability signal. We propose Denoised Conformal Alignment, which subtracts an estimated conditional variance component and combines conformal calibration with Benjamini--Hochberg selection. Our analysis shows that validity is governed by stability of proxy/oracle threshold labels, rather than pointwise perfection of the variance estimator. Experiments show substantially improved power while maintaining FDR control across challenging settings.

The rapid emergence of LLM-based agentic frameworks has significantly reduced the cost of assembling multi-agent systems (MAS), enabling fast prototyping and exploration of agentic behaviors. However, systems built with current tooling remain ill-suited for reliable, evolvable, and production-grade deployment. In practice, MAS are often developed in an ad-hoc and imperative manner, with agent logic, orchestration, observability, and control tightly interwoven, little to no explicit system-level validation, and development workflows optimized for demonstrations rather than long-lived, governed operation. As a result, behavior observed during experimentation rarely constitutes reliable evidence of behavior in production. In this paper, we introduce MAS-Lab, a specification-driven framework for principled development and experimental validation of multi-agent systems properties. MAS-Lab is designed to transform MAS from collections of scripts into engineered distributed systems by separating semantic intent from operational concerns, making behavior and control explicit, supporting reproducible experimentation, and preserving continuity across lifecycle stages. MAS-Lab consists of three layers: a declarative, framework-agnostic agentic specification layer (Spec); a stateful MAS Operating System that provides execution and control primitives plugged-in by design (MAS-OS); and a set of lab overlays with integrated observability and evaluation tools (Labs). Together, these components enable intent-based validation, principled system evolution, and a seamless transition to production-grade MAS.

Tool-augmented large language model agents increasingly operate over large tool libraries, but existing evaluations often focus on whether a model can call a tool correctly rather than how the visible tool menu shapes reliability, efficiency, and safety-relevant risk exposure. We introduce ToolMenuBench, a benchmark for evaluating tool-menu construction in multi-step LLM agents. ToolMenuBench varies tool-menu size, distractor type, state-dependent task structure, and risk exposure, and reports both filter-level and downstream agent metrics, including visible-tool count, risky-tool exposure, task success, wrong-tool calls, premature actions, and token usage. In a controlled evaluation across seven model backends, three tool-menu sizes, six filtering methods, and seven evaluation settings, CMTF improves task success from 32.1% under all-tools exposure to 85.7%, while reducing average token usage by roughly 98%. Causal minimal tool filtering achieves the strongest overall tradeoff, reducing visible tools, wrong-tool calls, premature actions, and risky-tool exposure relative to unfiltered exposure, lexical filtering, state-aware filtering, and broader causal-path baselines. ToolMenuBench provides a reusable evaluation framework for studying the agent-interface problem: which tools should be visible, when they should be visible, and under what cost or risk constraints.

As language-model agents increasingly work in teams, each agent must decide how much to trust its teammates. Yet we lack a standard way to measure trust between AI agents. We propose a behavioral measure based on costly verification. In a cooperative survival game, checking a teammate's work consumes resources, while trusting a wrong answer can be fatal. Relative to a memoryless version of the same model, reduced verification provides an observable measure of trust. Using this framework, we study trust formation, breakage, and recovery across six frontier model snapshots. When paired with a consistently reliable teammate, four snapshots (Claude Opus 4.6, Claude Sonnet 4.6, GPT-5.1, and Gemini 3.1 Pro) reduce verification by roughly 60-85%, whereas two smaller snapshots show little or no such adjustment. Failures reverse this discount, but models differ in how they respond. Some concentrate renewed scrutiny on the culprit, while others become more cautious toward the entire team. Recovery is slower than formation, and clustered failures sustain suspicion far longer than the same number of failures spread apart. These differences have practical consequences. Models that form trust verify less, decide more quickly, and achieve higher payoffs in our environment. By contrast, persistent over-verification is associated with indecision rather than safety. Our results show that trust dispositions can be measured before deployment and suggest that calibration, rather than maximal suspicion, should be the central concern in the governance of multi-agent AI systems.

LLM-based multi-agent systems increasingly coordinate planning, reasoning, tool use, and human interaction, yet their reliability remains limited. A central source of this limitation is the underspecified prompt--harness boundary. Current systems lack a principled way to decide which workflow commitments should remain in prompts and which should become harness structure. We present \textbf{XFlow}, an executable protocol programming system for reliable multi-agent workflows, and \textbf{XPF} (XFlow Protocol Format), its domain-specific protocol programming language. XFlow occupies a middle position between prompt-only orchestration and markup-like workflow descriptions. XPF remains readable as a literate protocol, but it is compiled and executed as a program. Its design keeps informal semantic work inside actors while moving selected commitments into harness structure that can be checked, preserved, and enforced. At runtime, XFlow stages uncertainty through lifecycle-governed symbols, which are typed state cells with validation and commit states. Actor outputs are mediated before they become shared state, instead of spreading through prompts, transcripts, or implicit memory. Our experiments cover Constrained Interaction, Long-Context Reasoning, and Agentic Software Engineering. They show that XFlow improves reliability by making constraints, evidence handling, and process requirements explicit and enforceable.

In equipment operation, the implementation of fault diagnosis is essential to ensure the continuity and safety of production equipment, improve operational efficiency and reduce maintenance costs. Since sensor readings are widely used for fault diagnosis, their reliability directly affects the results of fault diagnosis. A new fault diagnosis method is proposed to address the two problems of robustness assessment and robustness optimization of fault diagnosis models. For this purpose, a reliable fault diagnosis method based on a belief rule base (BRB) considering robustness analysis is proposed. Firstly, the robustness analysis of the BRB model is carried out systematically. Secondly, three robustness constraint strategies are proposed to optimize the robustness of the BRB fault diagnosis model. Finally, the effectiveness of the proposed model is verified by taking the fault diagnosis of WD615 diesel engine and Case Western Reserve University bearings as an example, and the experiments show that the proposed model improves both accuracy and robustness.

Autonomous web navigation remains challenging for LLM agents, and the strongest generalist systems rely on proprietary reasoning models whose inference cost is prohibitive for the repetitive tasks where such agents would be most useful. We argue this gap stems not from insufficient model capability but from agent architectures that fail to replicate three human cognitive advantages: selective attention to relevant page regions, persistent memory of website structure, and procedural fluency with common interaction patterns. We introduce WebChallenger, a web agent framework that addresses each gap through architecture design rather than model scale, built around PageMem: a structured page representation deterministically constructed from the DOM that exposes each page as a hierarchy of semantic sections with short summaries. On this shared substrate we build three mechanisms that mirror the three cognitive advantages: a divide-and-conquer observation pipeline that lets the agent skim section summaries and extract details only from task-relevant regions; a lightweight exploration and memory system that traverses each website once to build a reusable map of pages and element behaviors; and compound action workflows that collapse common multi-step interactions into single agent actions, handling partial state changes automatically. Because all three operate over PageMem, the framework generalizes across websites without site-specific adapters. Using off-the-shelf open-weight models without fine-tuning, our system achieves 56.3% on WebArena, 48.7% on VisualWebArena, 51.0% on Online-Mind2Web, and 70.9% on WorkArena, approaching frontier proprietary systems at a fraction of the cost. Our code is released at https://github.com/jayoohwang1/webchallenger

Safety judges are increasingly deployed to evaluate model outputs against evolving criteria, yet recent meta-evaluation work shows they remain brittle under prompt and rubric variation, with false negative-rate swings of up to 0.24 reported for stylistic perturbations alone. We argue that safety judgment is fundamentally a rubric-following problem: a robust judge must apply the given evaluation criteria consistently across rubric formulations rather than memorize one specific template. We propose a training strategy that combines (i) instance-conditioned dynamic rubrics generated from prompt-response-label triples to expose the judge to the variability of evaluation criteria, and (ii) a reliable-to-expressive curriculum that begins with clean fixed-rubric supervision and progressively introduces noisier dynamic-rubric data. We evaluate on a single human-labeled set under three contrasting rubric prompts (HarmBench-style, ShieldGemma-style, and a domain-specific rubric). Our 12B curriculum judge achieves 94.12-94.88% accuracy across the three rubrics with a cross-rubric range of only 0.76, outperforming general-purpose LLMs, dedicated safety classifiers, and reasoning-oriented judges up to 30B in both peak accuracy and stability. An ablation shows that naively mixing dynamic rubrics into SFT increases cross rubric variance (1.44 -> 3.60); only the curriculum schedule recovers and improves on the fixed rubric baseline (variance 0.76).

Mortality forecasting plays an important role in actuarial and policy decision-making, but its implementation remains technically complex and inaccessible to non-expert users. This project proposes a reliable large language model (LLM)-integrated interface that improves usability while maintaining statistical power. The LLM is designed as a constrained orchestration layer that translates natural-language inputs into structured configurations for a deterministic forecasting pipeline. A three-phase methodology is employed to ensure accuracy, usability, and transparency. First, a baseline pipeline is implemented using the CoMoMo package, reproducing established mortality forecasting results. Second, the pipeline is extended to generate multi-step forecasts using rolling-origin evaluation and mean squared error (MSE). Third, a prototype interface uses a local LLM to handle users' forecasting requests in plain language. The system demonstrates that LLMs can enhance accessibility without compromising reproducibility, transparency, or actuarial validity in high-stakes analytical workflows.

With PRECISE, we extended Prediction-Powered Inference to produce bias-corrected estimates of ranking evaluation metrics by combining a small human-labeled set with a large LLM-judged set. PPI is provably unbiased regardless of the LLM judge's error profile. We make it applicable to hierarchical metrics like Precision@K, where annotations are per-document but the metric is per-query, by reducing the output-space computation from O(2^|C|) to O(2^K). On the ESCI benchmark, augmenting 30 human annotations with Claude 3 Sonnet judgments reduces the standard error of Precision@4 estimates from 4.45 to 3.50 (a 21% relative reduction). In a production system, our framework correctly identified the best of three system variants from 100 human labels and 2 hours of domain-expert annotation; A/B testing confirmed this ranking with +407 bps in daily sales.

With the evolution of generative models, deepfakes have achieved near-perfect semantic realism, leaving forensic traces only in subtle structural anomalies. However, existing single-view paradigms often fail to generalize, as dominant semantic features overwhelm subtle artifact cues within entangled representations. This imbalance leads to overconfident yet brittle predictions -- a phenomenon we term the Semantic Masking Effect. To address this challenge, we propose a reliable framework called Divide-and-Conquer Multi-View Evidential Learning (DiCoME) for Deepfake Detection. In the "Divide" phase, we employ Geometric View Purification to decompose the entangled representation space through principled geometric projection. This process suppresses semantic interference within artifact-sensitive representations, forming the foundation for decorrelated yet complementary semantic and artifact views. In the "Conquer" phase, we leverage Uncertainty-Aware Evidential Learning to synthesize these distinct views. By explicitly modeling the "epistemic conflict" between semantic and artifact cues, this mechanism provides calibrated uncertainty estimates instead of forcing rigid deterministic decisions. Extensive experiments across multiple benchmarks demonstrate that our method consistently outperforms existing approaches in generalization performance, while providing reliable uncertainty estimation for trustworthy deepfake detection. Code is available at https://github.com/kxl0825/DiCoME.git.

Large Language Models (LLMs) excel at understanding natural language but struggle with optimisation tasks involving multiple constraints and user-defined preferences, which commonly arise in domains such as robotics. We propose a hybrid reasoning approach in which LLMs externalise reasoning through code generation. Given a natural language problem description, an LLM generates Python code that encodes user-defined constraints and preferences as a preference-based Maximum Satisfiability (MaxSAT) problem, which is then solved by an exact MaxSAT solver. To ensure correctness, solutions returned by the model-generated code are independently verified for feasibility and optimality against a canonical MaxSAT encoding, allowing for different encodings and multiple optimal solutions. We evaluate our approach using both open-source and closed-access LLMs on three families of preference-based reasoning tasks, and compare it against direct-answer, chain-of-thought, and program-of-thought baselines using the same models. While these baselines rarely produce feasible solutions, the MaxSAT-based pipeline achieves substantially higher acceptance rates, in some cases exceeding 80%. Our results demonstrate that LLM-driven code generation combined with preference-based MaxSAT enables solver-verifiable optimisation with respect to generated encodings, and substantially improves correctness under independently verified reference semantics.

LLM multi-agent systems often coordinate through natural-language dialogue or loosely structured shared memory, making intermediate state difficult to validate, attribute, and audit. We introduce PatchBoard, a schema-grounded collaboration architecture that replaces inter-agent dialogue with validated JSON Patch mutations over a shared structured state. An Architect agent constructs a task-specific schema and workflow rules, while a deterministic kernel validates each proposed state mutation against schema constraints, role-specific write contracts, and runtime invariants before committing it transactionally. On 630 matched ALFWorld episodes, PatchBoard achieves an 84.6% success rate, compared with 30.8% for LangGraph and 61.6% for Flock, while reducing tokens per successful task to 45.5k, compared with 368.3k and 64.2k, respectively.

Large language models (LLMs) are increasingly used for the automatic evaluation of generated text, yet most prior work focuses on English. Despite the growing demand for multilingual evaluation, extending LLM-based evaluators to multilingual settings remains challenging, particularly for low-resource languages and scenarios where in-domain data is scarce. This work explores several strategies for developing multilingual LLMs-as-a-judge, considering whether in-domain data is available for fine-tuning or not. We systematically analyze English, Spanish, and Basque, representing high-, mid-, and low-resource languages, considering instruction translation, monolingual versus multilingual supervision, and model size. For evaluation, we extend two existing meta-evaluation datasets to Basque and Spanish. Our results reveal key trade-offs: When in-domain data is available, fine-tuned smaller models can achieve performance comparable to proprietary models, whereas zero-shot evaluation with larger models proves more effective in out-of-domain settings. We also observe that fine-tuning on out-of-domain data can adversely affect model performance. These findings provide practical guidance for building efficient, reliable multilingual evaluation pipelines. The data and code are publicly available at hitz-zentroa/mJudge.

Activation oracles aim to make the activations of other models legible to humans and yield promising results compared to white-box interpretability techniques. However, uncertainty quantification (UQ) for the natural-language outputs of such activation oracles is so far understudied. Here, we investigate 6 different methods for estimating the confidence of activation oracles and evaluate how well-calibrated their confidence scores are. Our experiments on 6,000 samples per oracle (varying verbalizer and context prompts) reveal that bootstrap mode frequency is the best-calibrated method among those tested (ECE 5.7% vs. 25.5% for the answer-word log-probability on Qwen3-8B; 10.3% vs. 13.1% on Qwen3.6-27B), and that the log-prob baseline can serve as a fast triage signal at a fraction of the cost. Code and the patched trainer are available at https://github.com/federicotorrielli/probabilistic_activation_oracles.

Accurate estimation of the Angle of Progression (AoP) from intrapartum transperineal ultrasound is critical for objective assessment of labor progression, yet remains highly sensitive to imaging noise, boundary ambiguities, and the geometric amplification of local segmentation errors. We propose R2AoP, a reliable and robust AoP estimation framework that integrates structurally informed segmentation and confidence-guided geometric modeling to achieve stable and reproducible measurements. A three-branch local-structure-enhanced backbone improves the delineation of the pubic symphysis (PS) and fetal head (FH), while confidence-weighted contour fitting explicitly suppresses the influence of unreliable boundary points in AoP computation. To further improve performance under heterogeneous acquisition conditions, we introduce a lightweight geometry-reliable test-time adaptation strategy as an auxiliary component, enabling stable inference without target annotations. Extensive evaluations on multi-center benchmarks demonstrate consistent reductions in AoP error and boundary metrics compared with state-of-the-art AoP methods. Our source code is available at https://github.com/baiyou1234/R2AoP.

Vision-language models (VLMs) have achieved strong multimodal reasoning capabilities, but further improving them still relies heavily on large-scale human-constructed supervision for post-training. Such supervision is costly to obtain, especially for reasoning-intensive multimodal tasks where questions, answers, and feedback signals must be carefully designed. This motivates self-evolving learning, where a model improves itself through a dual-role closed loop: a questioner autonomously poses questions and a solver learns to solve them. However, we observe that current VLM self-evolving methods still face three major challenges: coarse-grained role alternation delays the interaction between question generation and solver adaptation; generated questions can progressively degrade in quality; and question types may collapse toward a narrow distribution. These issues limit the efficiency and reliability of self-evolution. Thus, we propose \textbf{RISE}, a reliable self-evolving framework for vision-language models. RISE is built on three complementary designs: fine-grained role alternation, which shortens the feedback loop between the questioner and the solver to improve efficiency; a quality supervisor, which improves question validity and pseudo-label reliability; and skill-aware dynamic balancing, which mitigates mode collapse and maintains broad skill coverage during evolution. Together, these components enable more reliable and effective self-evolution from unlabeled images. Experiments on two VLM backbones across seven benchmarks show that RISE consistently improves the base models, yielding broad and sustained gains. Our code is publicly available at https://github.com/AMAP-ML/RISE.

Random forests construct each tree with a different, randomised representation of the feature space. Their uniform voting cannot correct errors in regions where trees with incorrect representations probabilistically outnumber correct ones, even when the ensemble collectively holds enough correct information - a reducible error that this paper addresses. We propose using the structural pattern of each tree's decision path as an instance-adaptive reliability signal to identify and differentially weight the more reliable trees. At inference, a random forest reaches its prediction through the root-to-leaf path the sample traverses in each tree, so path-level reliability offers a finer granularity than tree-level weighting can access. We show that this signal reflects the actual reliability of each tree's decision, and that using it yields a statistically significant accuracy improvement over RF on 36 binary classification benchmarks (Wilcoxon p < 0.0001). Class-recall regression - the typical failure mode of RF correction methods - is measured: zero minority-recall regressions and a single majority-recall regression at the 0.2 pp threshold, indicating bias reduction rather than a class trade-off. We further quantify the reducible error accessible to the method from the fitted RF alone; this estimate correlates strongly with per-dataset gain (Pearson r = +0.840, p < 0.0001). On the qualifying group it identifies, the method delivers a mean +0.99 pp accuracy improvement with strict wins on every dataset (7/0/0); an optional amplification mechanism further raises this to +1.48 pp.

In many applications, human and LLM evaluators use assessments of relevant criteria to create an overall evaluation for an item or individual. For example, in admissions, committees assess candidates on attributes such as test scores, GPA, and research experience to evaluate their overall fit for the program. Another example arises in medical care where clinicians use patient reports of symptoms to consider preliminary diagnoses and assess risks. Each setting involves mapping multiple criteria to an overall evaluation -- a process that reflects the evaluator's underlying preferences. We focus on the fundamental question of learning these preferences. Many applications of this problem make specific modeling assumptions on evaluator preferences that may be substantially violated in the real world. We make the minimal assumption that the preference function is coordinate-wise non-decreasing, which is reasonable in a large number of evaluation settings. We theoretically characterize the severity of model mismatch for many common assumptions and show that it can lead to significant issues for learning evaluator preferences and other important downstream tasks. We then present an algorithm for learning evaluators' preferences that is robust to model mismatch. We prove theoretically that our algorithm can learn any preference function without sacrificing performance when the linearity assumption holds. Evaluations of our algorithm with synthetic simulations and real-world data confirm its ability to learn preferences robustly and illustrate key aspects of LLM and human preferences.

Deep learning models for medical imaging often exhibit overconfidence, creating safety risks in ambiguous diagnostic scenarios. While Conformal Prediction (CP) provides distribution-free statistical guarantees, standard methods such as Regularized Adaptive Prediction Sets (RAPS) optimize for average efficiency and can mask severe failures on difficult inputs. We propose an Adaptive Lambda Criterion for RAPS that minimizes the worst-case coverage violation across prediction set size strata. On OrganAMNIST (58,850 abdominal CT images, 11 classes), standard size-optimized RAPS converges to near-deterministic behavior with stratified undercoverage on uncertain samples, while our method achieves 95.72 percent global coverage with average set size 1.09 and at least 90 percent coverage across all strata. Cross-domain validation on PathMNIST (107,180 pathology images, 9 classes) confirms generalizability. Quantitative Grad-CAM analysis (rho = -0.30, p < 1e-22) shows that multi-label predictions correspond to focused attention on anatomically ambiguous regions. These results demonstrate that the proposed method improves reliability while maintaining efficiency, making it suitable for safety-critical medical AI applications.

Learning-assisted hyper-heuristics can select among dispatching rules while preserving the feasibility and interpretability of constructive Job Shop Scheduling Problem (JSSP) heuristics. Their main computational cost lies in label generation rather than model fitting, since each supervised label usually requires rolling out candidate rules from a partial schedule. We study this label-cost problem together with a reliability problem: a learned selector should not switch away from a strong default rule unless the predicted gain is credible. The proposed selector uses regret-normalized rollout labels, a contextual KNN uncertainty estimate, and a gate that acts only when the predicted improvement exceeds an uncertainty-adjusted margin. We also vary rollout depth and breadth to measure the cost-quality trade-off. On synthetic JSSP instances, the gated selector achieves the lowest mean RPD among learned selectors, remains close to the best fixed dispatching rule, and reduces Random-HH mean RPD by more than an order of magnitude.

Reliable inference requires that artificial intelligence (AI) models provide trustworthy uncertainty estimates, not merely accurate predictions. Recent advances in Bayesian learning have made significant progress toward this goal, and growing concerns about computational overhead have jointly shifted the design criterion from reliability alone to the co-design of reliability and efficiency, i.e., reducing computational overhead while preserving trustworthy uncertainty quantification. This thesis develops a unified framework from two perspectives to address the central question: can we efficiently perform reliable inference?

Modern predictive systems encode beliefs that can act as useful prior information for statistical inference in data-limited settings. Using them for prior construction introduces a tradeoff: an informative prior built from a predictive model can sharpen inference from limited data, but also risks propagating error from the model into the posterior. We propose a framework for AI-informed prior elicitation that mitigates this tension by rectifying the AI-induced law that generates synthetic data before using it to inform a prior. The rectified law can be embedded into synthetic data-driven prior elicitation techniques, including as a base measure in a Dirichlet process (DP) prior on the data-generating process. We refer to the resulting prior and corresponding posterior as the rectified AI prior and rectified AI posterior. We establish Gaussian asymptotics for the rectified AI posterior under non-vanishing prior strength and derive a first-order expression for its centering bias. Our rectified AI priors substantially reduce bias compared to standard approaches, improve the coverage of credible intervals, and make AI-powered prior information more reliable. We additionally apply the rectified AI prior to a real skin disease classification task and show that it can meaningfully boost predictive performance.

Modern Deep Learning (DL) workloads are increasingly deployed in safety-critical domains, such as automotive systems and hyperscale data centers, where transient hardware faults pose a serious threat to system reliability. These workloads are highly memory-intensive, and their correct functionality strongly depends on model parameters stored in memory, which are typically protected using Error Correction Codes (ECCs). In this work, we study ECC's impact on such models and propose two lightweight alternatives to ECCs that achieve superior reliability. The first approach, MSET, selectively hardens the most vulnerable bits in CNN and ViT parameters, while the second approach, CEP, provides fine-grained protection for all parameter bits. Experimental results demonstrate that both methods significantly enhance the reliability of large CNNs and ViTs, mostly outperforming conventional Single Error Detection Double Error Correction (SECDED) ECC schemes, with no memory overhead and, in fact, with considerably lower area and delay characteristics when compared to SECDEC. Experimental results indicate that ViTs can be effectively protected by merely protecting their highest exponent bits in FP16 and FP32 representations. Furthermore, applying the CEP technique can guarantee the resilience of DNNs by up to one order of magnitude higher BERs, with a 3.5x lower area overhead and 7x faster decoder compared to SECDED ECC.

Autonomous agents based on Large Language Models (LLMs) are increasingly being utilized in complex software systems. However, reliability remains a significant challenge due to unpredictable failures such as hallucinations, execution errors, and inconsistent reasoning. This paper proposes a reliability-aware self-healing framework for LLM-based software agents. The framework integrates failure detection, reliability assessment, and automated recovery mechanisms. First, we define a taxonomy of failure types and introduce a quantitative reliability assessment model. Next, we propose a failure detection method that identifies abnormal agent behavior based on execution patterns and output consistency. Finally, we design a self-healing mechanism that dynamically recovers from failures through adaptive replanning and corrective prompting strategies. The proposed framework was implemented in a multi-agent workflow environment and evaluated using real-world task scenarios. Experimental results demonstrate that our approach significantly increases task success rates, reduces failure propagation, and enhances overall system robustness compared to existing methods. In particular, this study distinguishes itself by establishing an integrated monitoring system that combines the agent's internal reasoning process with external execution results. These findings are expected to contribute to securing the stability of advanced autonomous systems and lowering the barriers to LLM adoption in production environments.

This paper presents the rAIson platform, a high-level technological environment for the development of automated, reliable and explainable decision-making agents. The research underlying the platform and its technological progress has now reached a mature stage that allows the platform to be used for the development of complex real-life applications without writing a single line of code.

Recent multi-bit watermarking methods for large language models (LLMs) prioritize capacity over reliability, often conflating decoding with detection. Our analysis reveals that existing ECC-based extractors suffer from catastrophic false positive rates (FPR), and applying rejection thresholds merely collapses detection sensitivity (TPR) to random guessing. To resolve this structural limitation, we propose BREW (Block-wise Reliable Embedding for Watermarking), a framework shifting the paradigm to designated verification. BREW employs a two-stage mechanism: (i) blind message estimation via independent block voting, followed by (ii) window-shifting verification that rigorously validates the payload against local edits. Experiments demonstrate that BREW achieves a TPR of 0.965 with an FPR of 0.02 under 10% synonym substitution, demonstrating that the high-FPR issue is not an inherent trade-off of multi-bit watermarking, but a solvable structural flaw of prior decoding-centric designs. Our framework is model-agnostic and theoretically grounded, providing a scalable solution for reliable forensic deployment.

Large language models (LLMs) have revolutionized Text-to-SQL generation, allowing users to query structured data using natural language with growing ease. Yet, real-world deployment remains challenging, especially in complex or unseen schemas, due to inconsistent accuracy and the risk of generating invalid SQL. We introduce Template Constrained Decoding (TeCoD), a system that addresses these limitations by harnessing the recurrence of query patterns in labeled workloads. TeCoD converts historical NL-SQL pairs into reusable templates and introduces a robust template selection module that uses a fine-tuned natural language inference model to match or reject queries efficiently. Once the template is selected, TeCoD enforces it during SQL generation through grammar-constrained decoding, implemented via a novel partitioned strategy that ensures both syntactic validity and efficiency. Together, these components yield up to 36% higher execution accuracy than in-context learning (ICL) and 2.2x lower latency on matched queries.

Multimodal large language models (MLLMs) are increasingly used to translate visual artifacts into code, from UI mockups into HTML to scientific plots into Python scripts. A circuit diagram can be viewed as a visual domain-specific language for hardware: it encodes timing, topology, and bit level semantics that are invisible to casual inspection yet safety critical once fabricated in silicon. Translating such diagrams into register-transfer-level(RTL) code therefore represents an extreme reliability test for vision-to-code generation. We reveal a phenomenon we call Mirage: replacing a circuit diagram with a blank image leaves Pass@k unchanged or even higher, because models bypass the visual input and instead exploit identifier semantics in the module header to retrieve canonical RTL templates. This constitutes a new, highly covert class of defect in AI-assisted code generation that directly undermines MLLMs' trustworthiness. To quantify the effect, we construct C2VEVAL and evaluate eight MLLMs under a paired Normal/Anony protocol in which Anony mode anonymizes all identifiers in both the diagram and the module header; Anony-mode scores drop sharply across all models, confirming that high Normal-mode accuracy is largely a Mirage. We then propose VeriGround (4B), trained with identifier anonymization, refusal augmentation, and D-ORPO (Decision-Focused ORPO) preference alignment that up-weights pivotal generate-or-refuse tokens. VeriGround achieves Functional Pass@1 of 46.11%/42.51%(Normal/Anony) with a False Refusal Rate of only 1.20%/0.00%, while maintaining >92% Refusal Rate on blank images. With only 4B parameters, VeriGround performs on par with GPT-5.4 under Normal and significantly outperforms all baselines under Anony, confirming genuine visual grounding.

We adapted the Reliable Change Index (RCI; Jacobson and Truax, 1991) from clinical psychology to item-level LLM version comparison on 2,000 MMLU-Pro items (K=10 samples at T=0.7). Two within-family pairs were tested: Llama 3 to 3.1 (+1.6 points) and Qwen 2.5 to 3 (+2.8 points). On the full benchmark, most items showed no reliable change (79% and 72%). However, over half the items were floor/ceiling. Among analysable items, change was bidirectional with large effect sizes: 34% improved and 28% deteriorated for Llama; 47% improved and 39% deteriorated for Qwen (median |delta p| = 0.50 and 0.90). Churn was asymmetric by difficulty: low-accuracy items improved, high-accuracy items deteriorated. Domain-level decomposition revealed family-specific reversals: Llama lost physics while Qwen lost law. Greedy single-shot evaluation missed 42% of reliably changed items and falsely flagged 25% of unchanged items. The aggregate accuracy gain is the net residual of opposing item-level movements. We recommend reporting churn rate alongside aggregate accuracy.

Visual Place Recognition (VPR) determines a query image's geographic location by matching it against geotagged databases. However, existing methods struggle with perceptual aliasing caused by irrelevant regions and inefficient re-ranking due to rigid candidate scheduling. To address these issues, we introduce FoL++, a method combining robust discriminative region modeling with adaptive re-ranking. Specifically, we propose a Reliability Estimation Branch to generate spatial reliability maps that explicitly model occlusion resistance. This representation is further optimized by two spatial alignment losses (SAL and SCEL) to effectively align features and highlight salient regions. For weakly supervised learning without manual annotations, a pseudo-correspondence strategy generates dense local feature supervision directly from aggregation clusters. Our Adaptive Candidate Scheduler dynamically resizes candidate pools based on global similarity. By weighting local matches by reliability and adaptively fusing global and local evidence, FoL++ surpasses traditional independent matching systems. Extensive experiments across seven benchmarks demonstrate that FoL++ achieves state-of-the-art performance with a lightweight memory footprint, improving inference speed by 40% over FoL. Code and models will be released (and merged with FoL) at https://github.com/chenshunpeng/FoL.

Coherent systems are representative of many practical applications, ranging from infrastructure networks to supply chains. Probabilistic evaluation of such systems remains challenging, however, because existing decomposition-based methods scale poorly as the number of components grows. To address this limitation, this study proposes the Reference-state System Reliability (RSR) method. Like existing approaches, RSR characterises the boundary between different system states using reference states in the component-state space. Where it departs from these methods is in how the state space is explored: rather than using reference states to decompose the space into disjoint hypercubes, RSR uses them to classify Monte Carlo samples, making computational cost significantly less sensitive to the number of reference states. To make this classification efficient, samples and reference states are stored as matrices and compared using batched matrix operations, allowing RSR to exploit the advances in high-throughput matrix computing driven by modern machine learning. We demonstrate that RSR evaluates the system-state probability of a graph with 119 nodes and 295 edges within 10~seconds, highlighting its potential for real-time risk assessment of large-scale systems. We further show that RSR scales to problems involving hundreds of thousands of reference states -- well beyond the reach of existing methods -- and extends naturally to multi-state systems. Nevertheless, when the number of boundary reference states grows exceedingly large, RSR's convergence slows down, a limitation shared with existing reference-state-based approaches that motivates future research into learning-based representations of system-state boundaries.