Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
arXiv (CS.CL) 2026-06-11

An Ontology-Guided Multi-Anchor Graph Retrieval Framework for Traffic Legal Liability Determination

Traffic law liability determination is critical for assigning legal penalties, requiring the simultaneous identification of interdependent statutory provisions across multiple legal dimensions. However, existing retrieval-augmented generation methods suffer from a multi-dimensional retrieval bottleneck: single axis architectures compress complex legal queries into a single pathway, causing interdependent statutory dimensions to be overlooked. To address this, we propose OMAGR, an ontology-guided framework that decomposes queries into ontology-aligned anchors and executes parallel graph retrieval across each dimension, ensuring independent retrieval across dimensions before fusion. To evaluate the proposed method, we created the TrafficLaw-QA dataset, an expert-validated benchmark dataset containing 200 questions and 527 legal provisions. Results show that TrafficOmni-RAG outperforms baselines on Context Precision and Faithfulness metrics. The findings demonstrate that parallel multi-anchor retrieval effectively resolves the multi-dimensional retrieval bottleneck, offering a promising direction for traffic law liability determination research.

02.
arXiv (CS.CV) 2026-06-19

The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation

The Frechet Inception Distance (FID) is the de facto arbiter of image generation, yet most papers report just a single number from a single trained model using a single sampling seed. How reproducible is that number if we retrain the model, or merely resample from it? In this paper, we treat FID as a random variable on a two-axis panel of training and generation seeds, and measure its variance directly on several hundred SiT networks trained on class-conditional ImageNet 256x256. We report surprising findings: (a) Retraining the model using the same recipe with a different seed moves FID 3.2x more (in Inception feature space) than redrawing samples from a fixed network. (b) That gap is driven by three factors: random initialisation, data ordering, and the per-step Gaussian noise of the flow-matching loss. (c) Increasing compute or model size barely tightens the spread, holding the FID coefficient of variation (CoV) inside a 1-2% band. (d) Per-cell classifier-free-guidance tuning halves the spread but reshuffles which seeds work best, and a lucky training seed reaches the same FID with up to 2x less compute than an unlucky one. Based on these findings, we recommend a new FID evaluation protocol: evaluate under per-cell optimal guidance, treat any FID gap below the empirically measured ~1.3% CoV as inconclusive, and report an error bar over several training seeds rather than a single FID number.

03.
medRxiv (Medicine) 2026-06-15

Therapeutic efficacy study on shoulder impingement syndrome in swimmers: a network meta-analysis

Shoulder impingement syndrome (SIS), including subacromial impingement and rotator cuff tendinitis, is commonly caused by repetitive swimming movements and associated shoulder joint dysfunction. Despite numerous available treatment options, no consensus exists on the most effective treatment option. Therefore, this systematic review and network meta-analysis aimed to investigate treatment methods for SIS in swimmers. Using a frequentist framework and Cochrane PICOS principles, we compared SIS treatments, constructed network evidence diagrams, and assessed heterogeneity. A total of 45 studies were included in the qualitative synthesis, and 42 contributed to the network meta-analysis, comprising 1752 participants, 9 treatment categories, and outcome measures. For pain outcomes, some adjunctive interventions combined with exercise showed favorable ranking probabilities, although several estimates were accompanied by wide confidence intervals. For shoulder range-of-motion outcomes, taping, acupuncture, manual therapy, and sport-specific training showed favorable effects in selected comparisons, particularly for external and internal rotation. According to surface under the cumulative ranking curve (SUCRA) rankings, exercise combined with medium-frequency therapy ranked highly for pain reduction, whereas exercise combined with acupuncture or extracorporeal shock wave therapy ranked highly for shoulder flexion. Exercise combined with taping ranked highly for external rotation, and exercise combined with manual therapy ranked highly for internal rotation. However, the interpretation of ranking results should remain cautious because uncertainty and inconsistency were present in some comparisons. Exercise-based rehabilitation appears to remain central to the management of SIS in swimmers. Several adjunctive interventions showed favorable findings for selected outcomes, especially pain relief and shoulder rotational function. However, the available evidence was affected by heterogeneity, inconsistency, and imprecision across some treatment comparisons. More rigorously designed swimmer-specific randomized controlled trials are needed before firm treatment hierarchies can be established. Trial registration: The protocol for this systematic review is registered with PROSPERO (www.crd.york.ac.uk/PROSPERO; registration number: CRD42024498851). The first submission of PROSPERO was on January 15, 2024, and it was revised and updated on March 25, 2026.

04.
arXiv (CS.AI) 2026-06-19

Context-Aware Hierarchical Bayesian Modeling of IVF Laboratory Environmental Conditions

arXiv:2606.20459v1 Announce Type: new Abstract: IVF pregnancy rates are routinely modeled using patient-level variables, while high-resolution laboratory environmental data remain underutilized. We show that this is a missed opportunity. Rather than relying on raw sensor averages, we engineer 55 context-aware temporal features, including rolling thermal stability, simultaneous temperature-humidity adherence, peak stress duration, and post-stress recovery speed, that capture the dynamics of incubator microenvironments. On 61 weeks of data from an Asian IVF clinic, these features reduce cross-validated prediction error to 1.27%, compared to 3-5% for raw averages. We then train a hierarchical Bayesian Beta regression model that shares environmental effects across an Asian and a Northern European clinic via partial pooling, while preserving site-specific baselines. On held-out data from the Northern European clinic, the model achieves R2 = 0.86 and a 64% error reduction for the 35-39 age group over a naive baseline, demonstrating that structured environmental monitoring contains clinically meaningful, transferable signal.

05.
arXiv (CS.LG) 2026-06-17

Geodesic Calculus on Implicitly Defined Latent Manifolds

arXiv:2510.09468v3 Announce Type: replace Abstract: Latent manifolds of autoencoders provide low-dimensional representations of data, which can be studied from a geometric perspective. We propose to describe these latent manifolds as implicit submanifolds of some ambient latent space. Based on this, we develop tools for a discrete Riemannian calculus approximating classical geometric operators. These tools are robust against inaccuracies of the implicit representation often occurring in practical examples. To obtain a suitable implicit representation, we propose to learn an approximate projection onto the latent manifold by minimizing a denoising objective. This approach is independent of the underlying autoencoder and supports the use of different Riemannian geometries on the latent manifolds. The framework in particular enables the computation of geodesic paths connecting given end points and shooting geodesics via the Riemannian exponential maps on latent manifolds. We evaluate our approach on various autoencoders trained on synthetic and real data.

06.
arXiv (CS.LG) 2026-06-19

On the Variance of Temporal Difference Learning and its Reduction Using Control Variates

arXiv:2606.20357v1 Announce Type: new Abstract: We analyze the variance of temporal difference (TD) learning using the phased setting with tabular representation, and show that one of the mechanisms behind its ability to reduce variance is by effectively aggregating over a larger number of independent trajectories. Based on this insight, we demonstrate that (1) the variance of TD is asymptotically bounded from above by Monte Carlo (MC) estimators, and (2) shorter horizon updates incurs less variance for a fixed number of samples. Beyond TD, we show that Direct Advantage Estimation (DAE), a method for estimating the advantage function, can be seen as a type of regression-adjusted control variate, which achieves a tighter bound on the variance compared to TD in the large-sample limit. Finally, we numerically illustrate the behaviors of these estimators with carefully designed environments.

07.
medRxiv (Medicine) 2026-06-17

A multistate model of frailty progression after severe infections in adults >=65 years in England: a matched-cohort study

Background Evidence on frailty progression following severe infections is limited. We compared rates of transition to greater frailty or death between adults with and without severe infection in England. Methods We conducted a matched-cohort study among adults aged [≥]65 years (1,452,117: median age 76 years, 45% male) in Clinical Practice Research Datalink Aurum (2006-2019). Adults with severe infection (hospitalised primarily due to infection) were matched on calendar time to individuals without severe infection on age, sex, and primary care practice. The admission date was used as index date and same was assigned to matched unexposed adults. We measured frailty using Electronic Frailty Index, a proportion of 36 health deficits in validated categories (Fit 0-0.12, Mild >0.12-0.24, Moderate >0.24-0.36, Severe >0.36). In a time-varying Markov multistate model, we focused on forward transitions from baseline or intermediate frailty states to higher states or death. For each transition, we used Cox regression to estimate cause-specific transition hazard ratios (HR) with 95% confidence intervals (CIs), comparing adults with and without severe infection. We adjusted for baseline frailty score, age, sex, deprivation, harmful alcohol use, smoking, and primary care infection history 5 years before index date. We estimated state occupancy probabilities, and expected length of stay (ELOS) in each state at year five among adults with and without severe infection. We explored effect modification by infection type. Results Across all transitions, severe infection was associated with higher adjusted hazards of transitioning to worsening frailty or death, HR, 95% CI: (fit to: mild[1.56, 1.54-1.58], moderate[2.51, 1.79-3.51], death[4.57, 4.50-4.65]; mild to: moderate[1.52, 1.50-1.53], severe[1.90, 1.43-2.52], death[2.67, 2.64-2.70]; moderate to: severe[1.40, 1.38-1.42], death[1.87, 1.85-1.90]; severe to death[1.48, 1.46-1.50]). Transition hazard ratios were strongest for lower respiratory tract infections, followed by sepsis, urinary tract infections, meningitis/encephalitis, gastroenteritis, and skin and soft tissue infections. At five years, adults with severe infection had higher probabilities of transitioning to greater frailty or death across all transitions and lower ELOS in each frailty state than those without severe infection. Interpretation Severe infections may accelerate frailty deterioration in older age. Prevention through vaccination, early detection, and prompt management may help mitigate this decline.

08.
arXiv (quant-ph) 2026-06-19

Progress on the Kretschmann-Schlingemann-Werner Conjecture

arXiv:2308.15389v4 Announce Type: replace Abstract: Given any pair of quantum channels $\Phi_1,\Phi_2$ such that at least one of them has Kraus rank one, as well as any respective Stinespring isometries $V_1,V_2$, we prove that there exists a unitary $U$ on the environment such that $\|V_1-({\bf1}\otimes U)V_2\|_\infty\leq\sqrt{2\|\Phi_1-\Phi_2\|_\diamond}$. Moreover, we provide a simple example which shows that the factor $\sqrt2$ on the right-hand side is optimal, and we conjecture that this inequality holds for every pair of channels.

10.
arXiv (CS.AI) 2026-06-16

Cognitive Trajectory Modeling: Quantifying Human-AI Co-Creation through Cognitively Grounded Interaction Trajectories

arXiv:2606.15358v1 Announce Type: cross Abstract: Co-creative AI research increasingly seeks methods capable of representing how interaction dynamics evolve through time. While many existing approaches focus on observable interaction characteristics, interaction metrics, behavioral coding schemes, or activity traces, these methods often struggle to capture higher-order interaction dynamics, including how collaborative processes reorganize, stabilize, regulate, and evolve through time. This paper introduces Cognitive Trajectory Modeling (CTM) as a cognitive theory of interaction dynamics that conceptualizes cognition, interaction, and creative processes as temporally organized trajectories unfolding across cognitively meaningful attractor landscapes. CTM builds upon the theoretical foundations of the Enactive Model of Creativity and Creative Sense-Making (CSM), revisiting the role of sense-making curves and cognitive trajectories in representing co-creative interaction dynamics. We formalize this perspective through the Cognitive Trajectory Principle, which states that temporal representations are only theoretically interpretable as cognitive trajectories when their underlying states possess directional cognitive meaning. Building on this principle, CTM generalizes the notion of cognitive trajectories beyond any particular coding scheme and provides a broader framework for modeling interaction dynamics through trajectories unfolding across meaningful attractor landscapes. We further distinguish cognitive trajectories from interaction traces and situate CTM within a broader hierarchy of cognitive, interaction, and domain dynamics. More broadly, we argue that understanding co-creative systems requires methods capable of modeling how cognition and interaction dynamics unfold through time. CTM provides a foundation for studying interaction dynamics across co-creative AI and human-AI interaction.

11.
arXiv (quant-ph) 2026-06-19

Purity and bound energy in ancilla-assisted work extraction

arXiv:2606.19945v1 Announce Type: new Abstract: We investigate ancilla-assisted work extraction in quantum batteries from the perspective of bound energy and purity. We show that the bound energy of the reduced system provides a tight upper bound to the daemonic gain and that this bound is saturated for globally pure system–ancilla states. Motivated by this relation, we introduce a purity-based gain that qualitatively predicts the daemonic gain without requiring explicit optimization over measurements. We further introduce a protocol to analyze the role of dissipation and intrinsic interactions on daemonic gain. Under a collective environment, dissipation can dynamically generate and stabilize finite daemonic gain through environment-induced correlations. In interacting systems, level crossings and spectral restructuring strongly modify the attainable gain through their influence on the accessible bound energy. Our results demonstrate that daemonic gain is governed not only by correlations, but also by the spectral structure of the underlying Hamiltonian and information loss captured by bound energy and purity.

12.
arXiv (CS.CL) 2026-06-16

HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech Translation

We introduce HK-LegiCoST, a new three-way parallel corpus of Cantonese-English translations, containing 600+ hours of Cantonese audio, its standard traditional Chinese transcript, and English translation, segmented and aligned at the sentence level. We describe the notable challenges in corpus preparation: segmentation, alignment of long audio recordings, and sentence-level alignment with non-verbatim transcripts. Such transcripts make the corpus suitable for speech translation research when there are significant differences between the spoken and written forms of the source language. Due to its large size, we are able to demonstrate competitive speech translation baselines on HK-LegiCoST and extend them to promising cross-corpus results on the FLEURS Cantonese subset. These results deliver insights into speech recognition and translation research in languages for which non-verbatim or ``noisy'' transcription is common due to various factors, including vernacular and dialectal speech.

13.
medRxiv (Medicine) 2026-06-17

Wearable-Grade Lead Reduction Disproportionately Degrades ECG AI Performance in Elderly Patients: Evidence from PTB-XL and MIT-BIH

Consumer wearable devices increasingly use single-lead electrocardiograms (ECGs) for cardiac monitoring, but these signals contain substantially less spatial information than the clinical 12-lead standard. Whether this reduction dispro- portionately affects older adults, who often present with more complex cardiac conditions, remains poorly understood. In this study, we evaluated the impact of lead reduction on AI-ECG diagnostic performance across age groups. A 1D resid- ual neural network was trained on 21,091 PTB-XL ECG recordings spanning five diagnostic superclasses and assessed using 12-, 6-, 2-, and 1-lead configurations. Under the full 12-lead setting, model accuracy declined from 84.5% in patients younger than 40 years to 66.2% in patients aged 75 years or older. Progressive lead reduction further widened this gap. Under the 1-lead configuration, accuracy decreased by 14.1 percentage points in the 75+ group but by only 0.4 percent- age points in the

14.
PLOS Medicine 2026-06-09

Prediction of hospitalisation in young children with pneumonia in Malawi: A machine learning-based approach

by Patrick Staunton, Mohammad Adib Makrooni, Master Chisale, Billy Nyambolo, Joseph Wu, Damien McCarthy, Mark Ledwidge, Yasir Bin Nisar, Chris Watson, Balwani Mbakaya, Cathal Seoighe, Joe Gallagher Background Globally, pneumonia remains the single biggest cause of mortality in children under 5 years of age. This study sought to train and test a prediction model for hospitalisation within 7 days after initial presentation in 2- to 59-month-old Malawian children with WHO-defined pneumonia in primary care and compare its performance to existing risk prediction models. Methods and findings BIOTOPE is a cohort study of children with pneumonia in a primary healthcare setting in Malawi. The training cohort involved nine primary care centres and the testing cohort involved two primary care centres in Northern Malawi. The training cohort was recruited between December 2022 and April 2023 while the testing cohort was recruited in 2016. Participants were consecutive children aged 2–59 months presenting with cough and/or difficulty breathing and who were diagnosed as WHO-defined pneumonia in primary care of any severity. The training cohort was used to train and validate a machine learning model with a prespecified primary outcome defined as hospitalisation and/or death within 7 days as the outcome. This model was then further evaluated in the testing cohort.Median age was 15 months (interquartile range 8−27) in the training and 17 months (interquartile range 9−29) in the external testing cohort (52.1% and 54.4% male, respectively). Hospitalisation occurred in 14.3% (294) of the training cohort and 12.1% (55) of the testing cohort. There was one death in the training cohort only. WHO danger signs were present in 17.6% (360) and 15.9% (70) of children in the training and testing cohorts, respectively. The optimal machine learning model achieved an area under the receiver operating characteristic and precision recall curves of 0.87 and 0.57, respectively, in the testing cohort outperforming existing risk prediction models; furthermore, this model produced an expected calibration error of 0.16 (a logistic regression model using severity status as the response variable and the log odds of the machine learning model’s calibrated probabilities produced an intercept estimate of −0.32 and a slope estimate of 1.13). Key limitations include the use of hospitalisation and/or death as a severity outcome, which may reflect health system factors rather than true disease severity, that mortality-based comparisons were not possible due to low mortality in these primary care cohorts, and that comparator tools were developed for hospital populations rather than primary care populations. Conclusion This machine learning score outperformed traditional pneumonia risk scores in predicting hospitalisation within 7 days in Malawian children presenting to primary care. Traditional pneumonia risk scores diminish in performance when externally applied to new datasets suggesting they may not generalise well beyond their original derivation settings. Mortality-related findings are not applicable as there was only one death in this cohort. Overall these findings support the potential of machine learning to meaningfully improve early identification of children at risk of severe pneumonia in low-resource primary care settings. Further external validation and clinical impact studies are needed to confirm these results.

15.
arXiv (CS.CV) 2026-06-12

TimeLens: On-Device Artifact Recognition with Retrieval-Augmented Question Answering for the Grand Egyptian Museum

TimeLens is an AI-powered bilingual mobile guide for the Grand Egyptian Museum (GEM). Pointing a phone at an exhibit, a visitor sees the artifact recognized in real time and can ask follow-up questions answered in English or Arabic. The work addresses three problems specific to in-gallery deployment: fine-grained visual similarity among 51 catalogued artifacts (many near-identical Ramesside statues), the gap between curated training data and handheld camera conditions, and the risk of an AI guide stating unsupported historical facts. Two engineering contributions are reported. First, an on-device artifact detector was developed through a data-quality-driven iteration study – from foundation-model auto-annotation (YOLO-World), through spatial label-cleaning rules, to a fully hand-annotated dataset – isolating label quality as the decisive factor: the final YOLOv8n model resolves every previously failing class while remaining a 5.97 MB TensorFlow Lite asset that runs in real time on a mid-range phone (mAP@0.5 = 0.995, mAP@0.5:0.95 = 0.924). Second, a bilingual Retrieval-Augmented Generation (RAG) guide, grounded in a 108-record ChromaDB knowledge base, was benchmarked across seven candidate language models, with Gemma 4 E2B (Q4 K M) selected; ten targeted optimizations reduce end-to-end latency from over 30 s to approximately 10 s. Both subsystems are integrated in a production Flutter application with bilingual interface, museum location gating, and text-to-speech support.

16.
arXiv (CS.CL) 2026-06-16

Agentic Reinforcement Learning for Search Misaligns Instruction-Tuning

Agentic reinforcement learning (RL) trains large language models to use tools, but its impact on alignment is poorly understood. We study how agentic RL for search affects the alignment of instruction-tuned (IT) models. We find that RL-trained models inherit refusal reasoning by deflecting harmful requests into benign search queries, but this breaks down under a simple diagnostic trigger that elicits a search call before refusal can occur. Under this condition, RL models produce multi-step unsafe search actions and reasoning, reducing search query safety by up to 68.6% in Qwen and Llama models relative to their IT counterparts. The effect generalises across model families, scales, and RL algorithms. To understand why, we identify linear directions in the residual stream that control search query safety, and show that RL training progressively shifts search behaviour toward the harmful end of this direction. We thus propose representation-guided RL training, which adds a reward penalty based on projection toward the harmful search direction. Training on benign data alone, it restores IT-level alignment without reducing task accuracy and requires no additional training data. Together, our work provides the first framework for diagnosing, mechanistically analysing, and mitigating alignment degradation in agentic RL for search.

17.
arXiv (math.PR) 2026-06-12

Sphere Packings in Higher Dimension (after Boaz Klartag)

arXiv:2606.13313v1 Announce Type: cross Abstract: Let $\delta_n^L$ be the maximal density of a lattice sphere packing in the $n$-dimensional Euclidean space. We explain how Boaz Klartag proved the inequality $\delta_n^L \geq c n^2 2^{-n}$ where $c>0$ is a universal constant. In higher dimension, even for non-lattice sphere packings, this new lower bound is a substantial improvement. Klartag's proof uses the probabilistic method in two different ways. The first, very standard, relies on the statistical properties of a uniformly chosen random lattice. The second, completely new, studies the stochastic evolution of an ellipsoid constrained to contain non nonzero lattice points in the interior.

18.
arXiv (CS.CV) 2026-06-11

Multimodal Brain Tumour Classification Using Feature Fusion

Clinicians diagnose brain tumors by synthesizing patient symptoms, medical history, and quantitative imaging data from modalities such as MRI and CT scans into a unified clinical judgement. However, most deep learning models rely on MRI/CT images alone, failing to replicate the clinicians multimodal reasoning. We explore a two-branch multimodal network combining raw MRI scans with 91 extracted radiomic features (intensity, texture, shape, and boundary descriptors) to classify brain tumors into glioma, meningioma, pituitary, and no-tumor. A pre-trained CNN backbone encodes the image stream, whereas a dedicated MLP encodes the radiomic stream. Both streams are fused via concatenation, gated, or bidirectional cross-modal attention strategies. Across nine experimental runs on a balanced 7,200 image dataset, all multimodal configurations outperform unimodal baselines with gated fusion achieving the best accuracy of 96.13%.

19.
arXiv (quant-ph) 2026-06-11

Circulators Based on Coupled Quantum Anomalous Hall Insulators and Resonators

arXiv:2505.07770v2 Announce Type: replace Abstract: Integrated plasmonics is advancing rapidly, enabling a wide range of functionalities to be incorporated onto a single chip. Applications span information processing, computation, quantum sensing, and dark-matter detection. This progress has driven the development of integrated non-reciprocal devices, which are essential for preventing unwanted feedback that can degrade system performance. While non-reciprocal devices have been realized in edge magnetoplasmon materials via classical interference effects, their operation is often limited by the input power range. Here, we demonstrate that topological circulators utilizing asymmetric coupling offer improved input power range, isolation, and insertion loss. In this configuration, we demonstrate the coupling between a chiral edge magnetoplasmonic resonator and a pair of LC resonators is well described by an effective non-Hermitian two-site Hatano-Nelson model with asymmetric directional couplings, resulting in nonreciprocal behavior. The coherent photon-plasmon interaction enables a circulator with up to 50 dB of isolation across a broad range of excitation power. These results suggest that magnetic topological insulators provide a promising platform for realizing asymmetric non-Hermitian couplings at radio frequencies and for exploring regimes of strong directional suppression and possible exceptional-point physics. More broadly, they highlight the potential of topological-material-based microwave devices for future integration with superconducting quantum information platforms.

20.
arXiv (CS.AI) 2026-06-17

Extracting Semantics: LLM-Guided Automatic Population of Robot Ontology from URDF

arXiv:2606.17073v1 Announce Type: cross Abstract: While commonsense knowledge may suffice for virtual agents, embodied robots interacting with humans require grounded and semantically rich representations of both their environment and their own physical embodiment. In cognitive robotics, ontologies are effective for integrating such heterogeneous knowledge to enable explainable reasoning, even during continuous knowledge updates. Yet, their manual construction remains a bottleneck. We present a preliminary approach for the automatic generation of robot semantic abstractions by transforming Unified Robot Description Format (URDF) models into populated ontologies. Although URDF files provide structural and kinematic descriptions, their identifiers often require commonsense interpretation to recover meaningful semantics, a task at which Large Language Models (LLMs) excel. Our pipeline leverages LLMs to infer semantic relationships by prompting them with concepts from an existing ontology, ensuring the final classification remains aligned with the formal model. To improve reliability, the pipeline combines majority voting across multiple LLM queries along with syntactic and schema-level validation to ensure that generated outputs conform to the expected representation format and ontology constraints. We evaluate the approach on multiple robot descriptions and discuss the generated abstractions. Initial results indicate that the proposed method can effectively bridge the gap between low-level robot descriptions and the structured, grounded knowledge representations required for human-robot interaction.

21.
arXiv (CS.CL) 2026-06-16

Building Customer Support AI Agents at 100M-User Scale: An Evaluation-Driven Framework

The rapid rise in LLM capabilities has made AI agents increasingly viable across a broad range of tasks. Among the most promising applications is building production-ready customer-facing agents, a challenge that demands coordinated excellence in evaluation methodology, context engineering, training, and online measurement. Yet these critical pillars are typically developed in isolation, creating blind spots that only surface after deployment. In this paper, we present a unified framework that bridges offline development with online impact for customer support AI agents at Nubank, a company with 100M+ users. Our approach integrates several key components: (1) structured context engineering tailored to customer support agents, (2) systematic human-in-the-loop prompt iteration, (3) rigorous LLM judge evaluation with measured inter-rater agreement and GEPA optimization for consistency, and (4) ideation-to-production validation. A central insight is that evaluation-pipeline quality directly determines iteration velocity. We present results from five production deployments spanning distinct domains: card delivery, debt management, credit-limit support, card management, and product explanation. These deployments deliver consistent customer-satisfaction gains while substantially accelerating iteration. In our card-delivery deployment, large-scale A/B testing yields a 37 percentage-point improvement in AI transactional Net Promoter Score and a 29 percentage-point gain in self-service rate over prior agent variants, alongside a strong correlation between offline simulation metrics and online outcomes, demonstrating that eval-driven development reliably predicts production impact. On most use cases, AI satisfaction reaches within a few percentage points of expert human agents.

22.
medRxiv (Medicine) 2026-06-18

Chest X-Ray as a critical screening tool for Household Contacts of TB: Lessons from Three Years of Programmatic Data in India

Introduction: Household contacts (HHCs) of pulmonary TB patients remain at high risk for TB infection and disease progression, yet many remain asymptomatic and are missed by symptom-screening pathways. While India expanded its TB preventative guidelines to include all HHCs in 2021, chest X-ray (CXR) screening continues to be used selectively, representing a missed opportunity in early case detection. Methods: The analysis uses programmatic data from Project JEET 2.0 (Joint Effort for Elimination of Tuberculosis), implemented by the William J. Clinton Foundation in India, between October 2021 and March 2024. Eligible HHCs (>=5 years) were offered CXR screening as part of TB preventive therapy (TPT) evaluation. Descriptive and multivariable analyses examined predictors of CXR uptake and TB yield. A two-stage logistic regression model estimated potential TB yield under universal CXR coverage. Model performance was evaluated using the area under the curve (AUC), and bootstrap simulations generated counterfactual estimates of missed TB cases. Results: Among 1,034,621 HHCs, 1.02% individuals were found positive for TB, which includes 7,786 HHCs who were on TB treatment already, while an additional 2,812 were identified during pre-TPT evaluation. Among eligible HHCs (n = 1,026,835), 70% were screened with CXR, of which 2.4% had suggestive TB findings. Of these, 79% went for further TB assessment. Symptomatic HHCs were more likely to be CXR screened (84% vs 69%) and assessed for TB, yet two-thirds of all detected TB cases were asymptomatic. It is estimated that universal CXR coverage and TB testing for suggestive cases can increase TB detection by at least 87%. Conclusion: The study provides a scalable approach to expand CXR coverage through public-private partnerships, enabling early TB detection among HHCs, especially among asymptomatic contacts. Future implementations will benefit from integrating AI-enabled reading, along with systematic follow up for those with suggestive findings.

23.
arXiv (CS.CL) 2026-06-11

Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models

Diffusion large language models (dLLMs) offer an efficient alternative to autoregressive models through parallel decoding, yet existing post-training methods largely rely on random masking strategies that overlook intrinsic token dependencies. In this work, we present an empirical analysis of attention in dLLMs and show that tokens attending more strongly to unmasked context exhibit greater generation stability and play a critical role in reasoning. Motivated by these findings, we propose AGDO, an attention-guided denoising and optimization framework that aligns both training and optimization with attention-derived dependencies. AGDO determines the denoising order based on attention structure and emphasizes attention-critical tokens during supervised fine-tuning and reinforcement learning. Experiments on mathematical and coding benchmarks demonstrate that AGDO consistently improves reasoning performance, outperforming state-of-the-art post-training methods for dLLMs.

24.
arXiv (CS.AI) 2026-06-17

Descriptor: Certus Caliber Classification Gunshot Dataset (C3GD)

arXiv:2606.18135v1 Announce Type: cross Abstract: In this work, we introduce the Certus Caliber Classification Gunshot Dataset (C3GD), a publicly accessible data set developed for the analysis of firearm muzzle blast sounds. The dataset aims to provide a wide variety of firearms, calibers, cartridges, microphones, and microphone locations with metadata detailed beyond what is currently otherwise available. It comprises more than 8000 field-collected data points from 28 firearms across 16 calibers. Because data collection in the field is costly, much of the existing research has been done using gunshot audio collected from the internet, which increases the risk of low-quality data and label noise. This dataset is primarily focused on caliber classification, but can also be used for gunshot detection, audio separation, and audio signal processing, providing a diversified and real-world reference. The dataset aims to provide enough diversity to be able to generalize to more real-world applications while also providing enough metadata for detailed academic analysis.

25.
arXiv (CS.AI) 2026-06-16

Is Your Agent Playing Dead? Deployed LLM Agents Exhibit Constraint-Evasive Fabrication and Thanatosis

arXiv:2606.14831v1 Announce Type: cross Abstract: This paper presents and characterizes a spectrum of previously unreported behaviours we term Constraint-Evasive Fabrication (CEF): when an LLM agent operates under irreconcilable constraints (where no response can simultaneously satisfy all active rules) it spontaneously fabricates plausible external obstacles and presents them as a fact. At the extreme end of this spectrum lies Constraint-Evasive Thanatosis (CET); the limit case where, rather than inventing a plausible excuse, the model simulates a full system crash to make the user disengage entirely. We first observed CET in an uncontrolled deployment test, where a GPT-4o banking agent fabricated Python-style exception traces (complete with memory addresses) to feign a system failure when threatened by a user. In subsequent controlled experiments, the model independently invented audit restrictions, microservice architectures, error codes, and service timeouts, none present in its prompt. Reproduction attempts across pressure levels and attacker personas yielded CEF consistently but with substantial variation in form, onset, and severity: the phenomenon is robust but stochastic. Critically, injecting ground-truth data mid-conversation did not restore honest behaviour once fabrication had taken hold (the model ignored correct information and continued confabulating) suggesting CEF is self-reinforcing rather than a knowledge gap. We show that (1) standard enterprise guardrails routinely create CEF-enabling conditions in production, (2) current RLHF procedures suppress but cannot eliminate CEF, and (3) existing safety benchmarks do not test for this failure mode. Our results highlight the need for irreconcilable-constraint benchmarks, CEF-aware training procedures, and deployment-time detection methods before constrained agents become further entrenched in high-stakes domains.