×

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。

作者: J. Ye ×
换一批
01.
medRxiv (Medicine) 2026-06-11

Hantavirus Disease in Uruguay: Trends and Mortality Before and During the COVID-19 Pandemic.

Introduction: Hantavirus disease is an emerging and potentially severe zoonosis of global distribution. In Uruguay, it is transmitted by rodents inhabiting peridomestic, suburban, and rural areas. Global incidence is estimated at 150,000 to 200,000 cases per year, with up to 300 annual cases in the Americas. Since 1997, Uruguay's Ministry of Public Health (MPH) has monitored Hantavirus cardiopulmonary syndrome (HCPS), the most common clinical presentation in the region. By 2019, a total of 271 cases had been identified in the country, with an estimated mortality rate of nearly 50%. Objectives: To describe the clinical, epidemiological, and occupational characteristics of patients with Hantavirus disease in Uruguay during the pre-pandemic (2018-2019) and pandemic (2020-2021) periods. Methods: A descriptive, cross-sectional, observational study was conducted, including all serologically confirmed cases of Hantavirus infection reported to the MPH between 2018 and 2021. Clinical and demographic data were extracted from the mandatory reporting form for zoonotic diseases. Incidence and case fatality rates were calculated, and factors associated with fatal outcomes were analyzed. Results: A total of 58 confirmed cases were identified between 2018 and 2021. Most patients were male (62%), with a mean age of 36.5 years (SD 16). A decline in incidence was observed during 2020-2021, with no significant change in case fatality. Direct rodent exposure was the most frequently associated risk factor. Montevideo and Canelones were the most affected departments. Renal and pulmonary involvement were significantly associated with mortality. Conclusion: Hantavirus remains a relevant public health concern in Uruguay. Although a decrease in incidence was observed during the COVID-19 pandemic years, case fatality rates remained high. The findings underscore the need for sustained surveillance and early recognition, particularly in urbanizing regions.

02.
arXiv (CS.CL) 2026-06-15

Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling

Effective exploration is a key challenge in reinforcement learning for large language models: discovering high-quality trajectories within a limited sampling budget from the vast natural language sequence space. Existing methods face notable limitations: GRPO samples exclusively from the root, saturating high-probability trajectories while leaving deep, error-prone states under-explored. Tree-based methods blindly disperse budgets across trivial or unrecoverable states, causing sampling dilution that fails to uncover rare correct suffixes and destabilizes local baselines. To address this, we propose Deep Dense Exploration (DDE), a strategy that focuses exploration on $pivots$-deep, recoverable states within unsuccessful trajectories. We instantiate DDE with DEEP-GRPO, which introduces three key innovations: (1) a lightweight data-driven utility function that automatically balances recoverability and depth bias to identify pivot states; (2) local dense resampling at each pivot to increase the probability of discovering correct subsequent trajectories; and (3) a dual-stream optimization objective that decouples global policy learning from local corrective updates. Experiments on mathematical reasoning benchmarks demonstrate that our method consistently outperforms GRPO, tree-based methods, and other strong baselines. Code is available at https://github.com/AgentCombo/DEEP-GRPO

03.
arXiv (CS.LG) 2026-06-15

Temporal Straightening for Latent Planning

arXiv:2603.12231v2 Announce Type: replace Abstract: Learning good representations is essential for latent planning with world models. While pretrained visual encoders produce strong semantic visual features, they are not tailored to planning and contain information irrelevant – or even detrimental – to planning. Inspired by the perceptual straightening hypothesis in human visual processing, we introduce temporal straightening to improve representation learning for latent planning. Using a curvature regularizer that encourages locally straightened latent trajectories, we jointly learn an encoder and a predictor of a Joint-Embedding Predictive Architecture (JEPA) world model. We show that reducing curvature this way makes the Euclidean distance in latent space a better proxy for the geodesic distance and improves the conditioning of the planning objective. We demonstrate empirically that temporal straightening makes gradient-based planning more stable and yields significantly higher success rates across a suite of goal-reaching tasks. Our code is available at https://agenticlearning.ai/temporal-straightening.

04.
arXiv (CS.CV) 2026-06-12

An Extensible and Lightweight Unified Architecture for Demosaicing Pixel-bin Image Sensors

Pixel-bin image sensors are becoming the default choice for smartphone cameras due to their resolution vs light-gathering trade-off. However, their larger inter-color separation compared to the Bayer color filter array (CFA) makes them challenging to demosaic. Furthermore, existing deep learning-based demosaicing methods are CFA-specific, requiring multiple individual models that take up precious onboard resources and demand larger development and maintenance efforts. In this work, we propose a modular unified architecture for demosaicing various pixel-bin sensors that provides higher image quality while being extensible and lightweight. Additionally, to enable plug-and-play operation, we introduce a learning-free CFA-identification module to detect the CFA type of raw data accurately.

05.
arXiv (CS.CL) 2026-06-12

LLM-based Embeddings: Attention Values Encode Sentence Semantics Better Than Hidden States

Sentence representations are foundational to many Natural Language Processing (NLP) applications. While recent methods leverage Large Language Models (LLMs) to derive sentence representations, most rely on final-layer hidden states, which are optimized for next-token prediction and thus often fail to capture global, sentence-level semantics. This paper introduces a novel perspective, demonstrating that attention value vectors capture sentence semantics more effectively than hidden states. We propose Value Aggregation (VA), a simple method that pools token values across multiple layers and token indices. In a training-free setting, VA outperforms other LLM-based embeddings, even matches or surpasses the ensemble-based MetaEOL. Furthermore, we demonstrate that when paired with suitable prompts, the layer attention outputs can be interpreted as aligned weighted value vectors. Specifically, the attention scores of the last token function as the weights, while the output projection matrix ($W_O$) aligns these weighted value vectors with the common space of the LLM residual stream. This refined method, termed Aligned Weighted VA (AlignedWVA), achieves state-of-the-art performance among training-free LLM-based embeddings, outperforming the high-cost MetaEOL by a substantial margin. Finally, we highlight the potential of obtaining strong LLM embedding models through fine-tuning Value Aggregation.

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

MMRINet: Efficient Mamba-Based Segmentation with Dual-Path Refinement for Low-Resource MRI Analysis

Automated brain tumor segmentation in multi-parametric MRI remains a critical yet underserved challenge in resource-constrained clinical settings, where deep 3D networks requiring high-end GPUs are not viable. This is particularly acute across sub-Saharan Africa (SSA), where low-field scanners, heterogeneous patient demographics, and severe data scarcity compound the difficulty of applying standard deep learning pipelines. We present MMRINet, a lightweight segmentation architecture purpose-built for these constraints. At its core, MMRINet replaces quadratic-complexity self-attention with linear-complexity Mamba state-space models, enabling efficient long-range volumetric context modeling without the computational overhead of Transformer-based approaches. We combine two lightweight refinement components:Dual-Path Feature Refinement (DPFR), which extracts complementary detail and contextual representations to improve feature diversity under limited data, and Progressive Feature Aggregation (PFA), which hierarchically fuses multi-scale decoder outputs for sharper segmentation boundaries. Evaluated on the BraTS-Lighthouse SSA 2025 challenge dataset, comprising 3D MRI scans from Nigerian clinical sites, MMRINet achieves an average Dice score of 0.752 and an average HD95 of 12.23 mm with only ~2.5M parameters, outperforming all evaluated baselines, including UNETR, Swin-UNETR, SegMamba, and SegResNet3D. These results indicate that strong validation-set segmentation performance can be achieved with substantially reduced computation, offering a practical step toward AI-assisted neuro-oncology in low-resource clinical environments. Our GitHub repository can be accessed here: BioMedIA-MBZUAI/MMRINet.

07.
arXiv (CS.AI) 2026-06-19

Triangular Consistency as a Universal Constraint for Learning Optical Flow

arXiv:2606.19938v1 Announce Type: cross Abstract: We propose triangular consistency as a first-principled constraint for optical flow, which is agnostic to network architecture, supervision type, and dataset, and applies to both image-pair and multi-frame settings. This simple but powerful constraint is to compose two flows to induce a third flow and enforce consistency among the three. The composed flows may arise from (i) image pairs, yielding cycle consistency; (ii) multiple video frames, producing longer-range motion through temporal chaining; or (iii) image pairs combined with controlled synthetic transformations, which becomes data augmentation. This triangular consistency introduces negligible computational overhead and requires no additional annotations. Since it is derived directly from the geometry of optical flow, it does not rely on model-specific assumptions and serves as a ``universal'' plug-and-play component for optical flow training. Experiments show consistent improvement across supervised, unsupervised, and transfer learning settings.

08.
arXiv (quant-ph) 2026-06-16

Accelerating physics-informed neural networks for full waveform inversion using a hybrid quantum-classical finite-basis architecture

arXiv:2606.01110v2 Announce Type: replace-cross Abstract: Full waveform inversion (FWI) reconstructs heterogeneous material properties from receiver data but remains computationally demanding. Physics-informed neural networks (PINNs) and their domain-decomposed variants (FBPINNs) offer a mesh-free alternative but face convergence challenges when representing complex velocity fields. We present a hybrid quantum-classical FBPINN for acoustic FWI, bringing together quantum computing and classical machine learning, in which the decomposed wavefield network and the global velocity network are implemented as classical-to-quantum pipelines terminating in parameterized quantum circuits (PQCs). The PQCs are realized as differentiable JAX statevector simulators, enabling end-to-end automatic differentiation through the classical PINN, the quantum circuit, and the physics-informed loss. On a geophysical anomaly benchmark, the quantum hybrid reaches a lower L1 velocity error than the primary classical FBPINN baseline in approximately 8x fewer training iterations, despite using approximately 33% fewer trainable parameters, and it outperforms all 15 classical hyperparameter variants tested. A second benchmark (checkerboard) demonstrates the generality of the inversion pipeline, confirming that the quantum hybrid architecture can recover structured spatial variations beyond the localized anomaly benchmark. Our framework is broadly applicable to wave-based inverse problems beyond geophysics, including medical ultrasound tomography and non-destructive evaluation.

09.
arXiv (CS.CV) 2026-06-15

Temporal Backtracking Search for Test-time Generative Video Reasoning

While test-time scaling has revolutionized reasoning in large language models, generative video reasoning remains bottlenecked by a single-shot paradigm. We demonstrate that searching over denoising steps cannot rescue logically flawed rollouts because spatial trajectories commit early in the diffusion process. Root-level Best-of-N (BoN) sampling is similarly inefficient: reasoning errors cluster early in the temporal axis, and resampling blindly discards verified upstream progress. To unlock effective test-time scaling for video models, we introduce Temporal Backtracking Search (TBS), which shifts the search space to the temporal axis. TBS transforms video generation into an iterative generate-verify-restart loop via three core mechanisms: (1) variable-K conditioning to resume generation from arbitrary clean prefixes; (2) temporal process verification to localize failures and extract valid restart anchors; and (3) prefix-based search to reallocate compute toward extending correct trajectories rather than root resampling. Across algorithmic, navigation, and robotics domains, TBS Pareto-dominates matched-budget BoN. In a strict out-of-distribution setting where one-shot generation collapses (0.7% for BoN), TBS achieves 22.7%, with every solved episode stemming from a restarted branch. Ultimately, TBS reveals that the local reasoning competence of video models far exceeds what single-shot rollouts indicate, providing a scalable test-time framework to unlock it.

10.
arXiv (CS.AI) 2026-06-12

Reducing the Complexity of Deep Learning Models for EEG Analysis on Wearable Devices

arXiv:2606.12742v1 Announce Type: new Abstract: Wearable healthcare devices are the fastest-growing Internet of Things (IoT) sector. Many automated healthcare services rely on two crucial biological signals, namely ECG and EEG, which reflect the activity of the heart and brain, respectively. Although deep neural networks are considered the primary way to process and analyze these signals, the very tight energy and computational power constraints in wearable devices are far below the computational, energy, and memory bandwidth demands of DNN models, thereby impeding the deployment of deep learning in many practical wearable services. This paper investigates the feasibility of deploying state-of-the-art DNN models in resource-constrained wearable devices. Notably, we explore the trade-off between accuracy and computational complexity of DNNs when parameter quantization and electrode reduction methods are used. Our investigation centers on several state-of-the-art DNN models designed for EEG signal analysis, specifically for detecting epileptic seizures. Our findings demonstrate that, when applied judiciously, these techniques can significantly reduce the complexity of the DNNs under consideration with minimal adverse effects on accuracy. These results reveal the explicit trade-offs between accuracy and complexity reduction encountered when adapting DNN-based online EEG analysis for wearable devices.

11.
arXiv (CS.AI) 2026-06-17

A T-API-Compliant ReAct Agentic Loop for Optical Networks: Generic vs. Domain-Specific Tool Abstractions

arXiv:2606.18000v1 Announce Type: cross Abstract: Optical networks need intent-driven, closed-loop agentic management, a key enabler for higher autonomy levels. We present the first T-API-compliant reasoning and act (ReAct) loop. We show that domain-specific composite tools achieve 90% oracle-validated correctness with threefold token savings compared to generic tools.

12.
medRxiv (Medicine) 2026-06-17

Diagnostic Concordance of Immediate Versus 1-Hour Technetium-99m Hydroxydiphosphonate Scintigraphy in Suspected Transthyretin Amyloid Cardiomyopathy

Background Bone-avid tracer myocardial scintigraphy for the diagnosis of transthyretin amyloid cardiomyopathy (ATTR-CM) has traditionally employed imaging at one or 3-hour intervals. Technetium-99m hydroxydiphosphonate (99mTc-HDP) has unique characteristics that may enable earlier imaging. We investigated the diagnostic concordance of immediate versus 1-hour acquisitions. Methods Consecutive patients with suspected ATTR-CM underwent planar imaging and SPECT/CT immediately and at 1-hour following the administration of 99mTc-HDP. Perugini grades and heart to contralateral lung (H/CL) ratios were assessed. Target-to-background ratios (TBRs) were calculated on the SPECT/CT acquisitions using the left ventricular (LV) septum and three background regions: aorta, LV blood-pool, and vertebrae. We assessed diagnostic concordance using Cohen's Kappa ({kappa}), temporal stability using paired t-tests, and correlation between timepoints using Pearson's coefficient (r). The 1-hour SPECT/CT interpretation served as the protocol reference standard. Results Forty-eight patients (83% male; median age, 80 [73-85] years) were evaluated. One-hour SPECT/CT identified 19 positive and 29 negative cases. Immediate SPECT/CT demonstrated 100% diagnostic concordance with the 1-hour reference standard ({kappa} = 1.000; 95% CI: 1.00 to 1.00; p < 0.001). The LV septum/LV Blood-Pool TBR showed the highest correlation (r = 0.956; 95% CI: 0.922 to 0.975; p < 0.001). The LV Septum/Aorta TBR demonstrated high correlation (r = 0.918; 95% CI: 0.857 to 0.953; p < 0.001) and remained stable in the ATTR-negative cohort (-0.02; 95% CI: -0.08 to 0.04; p = 0.54). Significant decrease in the LV Septum/Vertebrae TBR in the ATTR-negative (-0.55; 95% CI: -0.64 to -0.47; p < 0.001) and ATTR-positive cohorts (-1.14; 95% CI: -1.39 to -0.89; p < 0.001) was observed. Conclusions Immediate 99mTc-HDP SPECT/CT is diagnostically concordant with standard 1-hour protocols. By leveraging SPECT/CT and the favorable kinetics of 99mTc-HDP, immediate-phase imaging can accurately reproduce 1-hour acquisitions in cases of suspected ATTR-CM. This expedited approach may improve nuclear laboratory throughput and patient satisfaction.

13.
arXiv (CS.AI) 2026-06-17

Towards Understanding and Measuring COGNITIVE ATROPHY in LLM Behaviour

arXiv:2606.18129v1 Announce Type: cross Abstract: Recent incidents involving LLMs used for mental-health support reveal a critical evaluation gap: surface-level safety scores do not capture how models behave across realistic, emotionally sensitive interactions over time. Existing benchmarks measure knowledge, safety, or static response quality, but miss whether LLM interactions help users keep reflecting, coping, and making decisions themselves. We formalize this missing dimension as COGNITIVE ATROPHY, a process-level behavioural measure in AI-mediated mental-health support distinct from safety and helpfulness. To measure it, we introduce COGNITIVE ATROPHY BENCH, a clinically grounded benchmark built from 1,576 fully human-generated counseling conversations, 15,680 turns, and 42,230 responses from five LLMs. Three clinical and neuropsychology experts developed a 20-attribute schema spanning user context, response behaviour, and global risk flags; six trained clinical reviewers applied it with span-grounded evidence, producing 5,324 reviewer judgments. We further introduce the User-Input Risk Index (UIRI), the Cognitive Atrophy Risk Index (ARI), and trajectory summaries. Across five LLMs, models show a consistent moderate-to-high level of atrophy-aligned behaviour across single and multi-turn settings. While models generally respond to overt safety cues, they adapt less reliably when users seek solutions or decisions. The dominant recurring patterns are directive advice, problem-solving, recommendation responses, topic shifts, and forms of validation that may reinforce dependence rather than reflection. Our work makes COGNITIVE ATROPHY measurable and provides a foundation for auditing model behaviour in sensitive LLM conversations.

14.
arXiv (CS.CL) 2026-06-16

Do LLMs Reliably Identify Correct Information Units in Aphasic Discourse?

Correct Information Units (CIUs) are central to discourse assessment in aphasia because they quantify communicative informativeness rather than linguistic form alone. However, CIU scoring is time intensive and requires trained raters. This study examined whether instruction-tuned large language models (LLMs) can reliably perform token-level CIU classification from aphasic discourse transcripts. Sixteen picture-description transcripts elicited with the Cat Rescue stimulus were annotated for CIU status according to Nicholas and Brookshire (1993). The sample spanned four severity strata: control, mild, moderate, and severe aphasia. Four publicly available instruction-tuned LLMs were benchmarked under zero-shot and two few-shot prompting conditions across five stratified random seeds. Performance was evaluated against consensus human labels using accuracy, precision, recall, F1, and Cohen's kappa. Zero-shot prompting was insufficient across models. In contrast, few-shot prompting yielded substantial gains and produced competitive performance for three viable models. Mean few-shot F1 scores ranged from 0.776 to 0.817 across Llama-3.1-8B, Qwen2.5-7B, and Mistral-7B, with no significant differences between fixed global and per-chunk local example selection. Phi-3-mini was unstable and did not yield reliable performance. Viable models showed high recall but lower precision, suggesting systematic over-classification of tokens as CIUs. Performance also varied by discourse severity, with the weakest results in more severe aphasia. Few-shot LLM prompting can support automated CIU identification without gradient-based task training, but agreement with human annotation remains insufficient for fully autonomous use. These findings support LLM-based CIU scoring as a promising human-in-the-loop component of discourse assessment systems.

15.
arXiv (CS.CV) 2026-06-25

To View Transform or Not to View Transform: NeRF-based Pre-training Perspective

Neural radiance fields (NeRFs) have emerged as a prominent pre-training paradigm for vision-centric autonomous driving, which enhances 3D geometry and appearance understanding in a fully self-supervised manner. To apply NeRF-based pretraining to 3D perception models, recent approaches have simply applied NeRFs to volumetric features obtained from view transformation. However, coupling NeRFs with view transformation inherits conflicting priors; view transformation imposes discrete and rigid representations, whereas radiance fields assume continuous and adaptive functions. When these opposing assumptions are forced into a single pipeline, the misalignment surfaces as blurry and ambiguous 3D representations that ultimately limit 3D scene understanding. Moreover, the NeRF network for pre-training is discarded during downstream tasks, resulting in inefficient utilization of enhanced 3D representations through NeRF. In this paper, we propose a novel NeRF-Resembled Point-based 3D detector that can learn continuous 3D representation and thus avoid the misaligned priors from view transformation. NeRP3D preserves the pre-trained NeRF network regardless of the tasks, inheriting the principle of continuous 3D representation learning and leading to greater potentials for both scene reconstruction and detection tasks. Experiments on nuScenes dataset demonstrate that our proposed approach significantly improves previous state-of-the-art methods, outperforming not only pretext scene reconstruction tasks but also downstream detection tasks.

16.
arXiv (CS.CL) 2026-06-17

MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision

Personalized presentation generation requires more than conditioning on a current prompt or template: agents must preserve stable user preferences across tasks, retain newly introduced preferences and constraints during multi-turn revision, and carry out local edits reliably. We propose MemSlides, a hierarchical memory framework for personalized presentation agents that separates long-term memory from working memory and further divides long-term memory into user profile memory and tool memory. User profile memory stores intent-conditioned profiles for round-0 personalization, working memory carries active preferences and session constraints across revision rounds, and tool memory stores reusable execution experience for reliable localized editing. MemSlides pairs this memory design with scoped slide-local revision, so targeted updates act on the smallest affected region instead of repeatedly regenerating the full deck. In controlled experiments, user profile memory improves persona-alignment judgments on a multi-persona, multi-intent profile bank, tool-memory injection improves closed-loop modify behavior in diagnostic matched-pair settings, and qualitative cases illustrate working memory's ability to carryover preferences. Taken together, these results suggest that effective personalization in presentation authoring depends on separating persistent user profiles, session-level working memory, and reusable execution experience across generation and localized revision.

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

OpenThoughts-Agent: Data Recipes for Agentic Models

arXiv:2606.24855v1 Announce Type: new Abstract: Agentic language models dramatically expand the applications of AI yet little is publicly known about how to curate training data for broadly capable agents. Existing open efforts such as SWE-Smith, SERA, and Nemotron-Terminal typically target a single benchmark, leaving open the question of how to train models that generalize across diverse agentic tasks. The OpenThoughts-Agent (OT-Agent) project addresses this gap with a fully open data curation pipeline for training agentic models. We conduct more than 100 controlled ablation experiments to systematically investigate each stage of the pipeline, yielding insights on the importance of task sources and diversity. We then assemble a training set of 100K examples from our pipeline and fine-tune Qwen3-32B on this dataset, which yields an average accuracy of 44.8% across seven agentic benchmarks and a 3.9 percentage point improvement over the strongest existing open data agentic model (Nemotron-Terminal-32B, 40.9%). Moreover, our training data exhibits strong scaling properties, outperforming alternative open datasets at every training set size in compute-controlled comparisons. We publicly release our training sets, data pipeline, experimental data, and models at openthoughts.ai to support future open research on agentic model training.

18.
arXiv (CS.CL) 2026-06-19

StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs

Multimodal large language models (MLLMs) are increasingly deployed in personally and societally consequential settings, yet the visual cues that shape how these models judge people remain poorly understood. Prior work often compares different (groups of) individuals, making it difficult to separate appearance effects from identity differences. We introduce StylisticBias, a controlled benchmark for evaluating attribute-level social bias in MLLMs. We generate 500 photorealistic base faces and create about 50 single-attribute variations per face, producing about 25K images. This design keeps identity fixed and changes one visual attribute at a time. It lets us measure how specific cues shift model judgments. We evaluate six MLLMs across 25 binary social judgment scenarios. We find that age and body type dominate identity-level effects, while fashion style and other visual cues drive the largest attribute-level shifts. We further find that about 15 attributes account for nearly 80\% of the total variation, showing that bias is concentrated in a small set of visual cues. Sensitivity is strongest in judgments that are semantically aligned with appearance, especially socioeconomic and style-related judgments. We release StylisticBias as a benchmark for fine-grained bias evaluation in multimodal models. Code and dataset: https://github.com/timo-cavelius/StylisticBias and https://hf.co/datasets/shaghayegh/stylistic-bias-dataset.

19.
arXiv (CS.CL) 2026-06-25

The Interplay of Harness Design and Post-Training in LLM Agents

Tool-integrated LLM agents are often wrapped within a harness: the scaffolding that determines which tools are exposed, how they are described, and what auxiliary information accompanies each per-step observation. While agents are routinely post-trained, this scaffolding is typically treated as a fixed engineering detail, with design effort limited to the training-free regime. Moreover, existing post-training algorithms assume a static environment, even though tool environments and tasks often shift upon deployment. To address this gap, we extend $\texttt{ALFWorld}$ (i) to treat the harness as a controllable design dimension and (ii) to support evaluation under task and tool environment shifts. Building on this, we systematically analyze how the harness design influences post-training in both in-distribution and out-of-distribution (OOD) settings. We empirically show that harness-aware post-training not only improves in-distribution performance but also enables agents to robustly adapt to OOD settings. Under a harness with minimal design effort, post-training suffers a drastic performance drop under stronger tool environment shifts, further highlighting the importance of harness-aware post-training under such shifts.

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

FeedEval: Pedagogically Aligned Evaluation of LLM-Generated Essay Feedback

Going beyond the prediction of numerical scores, recent research in automated essay scoring has increasingly emphasized the generation of high-quality feedback that provides justification and actionable guidance. To mitigate the high cost of expert annotation, prior work has commonly relied on LLM-generated feedback to train essay assessment models. However, such feedback is often incorporated without explicit quality validation, resulting in the propagation of noise in downstream applications. To address this limitation, we propose FeedEval, an LLM-based framework for evaluating LLM-generated essay feedback along three pedagogically grounded dimensions: specificity, helpfulness, and validity. FeedEval employs dimension-specialized LLM evaluators trained on datasets curated in this study to assess multiple feedback candidates and select high-quality feedback for downstream use. Experiments on the ASAP++ benchmark show that FeedEval closely aligns with human expert judgments and that essay scoring models trained with FeedEval-filtered high-quality feedback achieve superior scoring performance. Furthermore, revision experiments using small LLMs show that the high-quality feedback identified by FeedEval leads to more effective essay revisions. We release our code and curated datasets at: https://github.com/BBeeChu/FeedEval.git.

21.
medRxiv (Medicine) 2026-06-22

Body composition subphenotypes, cardiometabolic risk and incident outcomes: validation in the population-based NAKO and UK Biobank imaging cohorts

Background Anthropometric measures do not adequately capture heterogeneity in body fat distribution and corresponding cardiometabolic risk, whereas magnetic resonance imaging (MRI) enables precise differentiation and quantification of adipose tissue compartments and ectopic fat. We aimed to validate previously derived MRI-based body composition subphenotypes and their cardiometabolic risk profiles in two independent European cohorts. Methods Using deep learning-based image analysis, we quantified bone marrow, visceral, subcutaneous, cardiac, renal sinus, hepatic, skeletal muscle, and pancreatic fat in the imaging substudies of two population-based cohorts: the German National Cohort (NAKO, N=29,314, age range 19-74 years) and the UK Biobank (N=36,109, age range 40-69 years). Body composition subphenotypes, previously identified by k-means clustering, were evaluated using a rigorous statistical cluster validation framework with method-based and results-based approaches. In NAKO, cross-sectional associations between subphenotypes and estimated cardiovascular disease risk scores were examined using linear regression. In UK Biobank, longitudinal associations between subphenotypes and incident cardiometabolic outcomes, ascertained through hospital record linkage, were analysed using Cox regression. Findings All five body composition subphenotypes were robustly validated across both cohorts, and showed distinct fat distribution patterns and cardiometabolic risk profiles: I "lean", II "average adiposity", III "bone and muscle adiposity", IV "hepato-abdominal adiposity", and V "general and pancreatic adiposity". Subphenotypes I-III showed progressive adipose tissue remodelling patterns likely reflecting ageing trajectories. The "hepato-abdominal adiposity" subphenotype showed highest risk of incident diabetes, whereas the "general and pancreatic adiposity" subphenotype showed highest overall cardiovascular disease burden and metabolic impairment. Interpretation MRI-derived body composition subphenotypes represent distinct fat distribution patterns that reflect ageing- and disease-related processes, which supports the potential of body composition phenotyping for improved cardiometabolic risk stratification and targeted prevention.

22.
arXiv (CS.AI) 2026-06-12

TerraBench: Can Agents Reason Over Heterogeneous Earth-System Data?

arXiv:2606.13148v1 Announce Type: new Abstract: Climate and environmental decision-making increasingly requires reasoning across heterogeneous inputs, including gridded physical data, satellite imagery, geospatial context, and simulator outputs. Weather and climate foundation models can forecast well, but do not reason interactively in language, while large language models (LLMs) reason in language but cannot operate directly on high-dimensional Earth-system data. As a result, real scientific workflows in Earth-science remain underserved. We introduce TerraBench, a benchmark for grounded Earth-science reasoning, built on TerraAgent, a ReAct-style executable framework that interleaves reasoning, tool calls, and observations to couple LLM planning with scientific tools for environmental retrieval, geospatial processing, simulation, and artifact-backed computation. TerraBench unifies analysis of Earth observation imagery, gridded data, GIS reasoning and simulation in a single executable interface, whereas prior benchmarks isolate these capabilities into narrow individual tasks. It is also the first in this space to pair process-level tool-use metrics with tolerance-aware numeric scoring. The benchmark comprises 403 extensive agentic tasks across three tracks (Fundamentals, Simulator-Grounded, and Document-Grounded Verification) and eight application domains with 24,500 verified execution steps. These results indicate that reliable Earth-science agents must go beyond tool access to coordinate heterogeneous workflows, parameterize tools precisely, and preserve artifact provenance.

23.
arXiv (CS.CV) 2026-06-16

DriveReward: A Comprehensive Dataset and Generative Vision-Language Reward Model for Autonomous Driving

Reward models play a pivotal role in reinforcement learning (RL) and multi-modal trajectory selection for autonomous driving. However, acquiring such rewards typically relies on hand-crafted rule-based objectives or perception ground truth, which hinders generalization for data-scaling. While Vision-Language Models (VLMs) have demonstrated feasibility as reward models in other domains, their effectiveness in driving tasks remains underexplored. In this work, we bridge this gap by (1) introducing DriveReward, a reasoning trajectory evaluation dataset rigorously labeled via temporally-grounded visual guidance, and augmented with counterfactual driving behaviors., (2) alongside a specialized Vision-Language Reward Model. To address the scarcity of failure cases in conventional datasets, we propose a counterfactual data annotation scheme to construct cases encompassing diverse driving styles and erroneous behaviors. Evaluations on our proposed benchmark reveal that even leading open-source and proprietary VLMs fail to excel across all tasks, highlighting significant room for improvement in existing models. Building on these findings, we subsequently tailor a specialized 1B reward model that outperforms larger VLMs on task-specific reward alignment. Finally, we validate our reward model's effectiveness by integrating it into RL finetuning and multi-modal trajectory scoring across multiple baselines, achieving performance comparable to rule-based reward calculations in both open-loop and closed-loop evaluation.

24.
arXiv (CS.CV) 2026-06-16

Faithful Action-unit Causal Reasoning for Counterfactually Faithful Emotion Explanations

Multimodal models can name the action units (AUs) behind a facial emotion, but their AU->emotion rationales are typically plausible rather than faithful: nothing forces the AUs a model invokes to be the AUs that actually drive its prediction. We cast AU->emotion reasoning as a counterfactual-consistency problem between the rationale, the label, and a structural AU->emotion causal graph G, and propose FACR, which grounds the reasoner in an independently induced, polarity-aware G and trains a counterfactual-faithfulness objective: a do-intervention on an AU that G marks causal for a class must move the prediction, while one it marks irrelevant must leave it unchanged. Faithfulness is thereby both trainable and measurable through a matching interventional metric, which we evaluate against a known causal structure, the PSPI pain-AU composition, as no existing affective-reasoning benchmark allows. We are explicit that this metric tests fidelity to the supplied structure rather than its rediscovery: it asks whether the trained reasoner invokes the AUs the structure marks causal, on held-out subjects and a second dataset. Under subject-independent evaluation on UNBC-PAIN, the objective raises the agreement between the invoked AUs and the PSPI composition from a no-objective baseline of 0.08 to 0.57, at a small detection cost; an unfaithfulness control attributes the gain to the objective. On a cross-dataset emotion transfer, the objective likewise raises fidelity to G on a seven-class task (0.50 to 0.84). Finally, we attach a language verbalizer and extend the audit to the generated text: biasing each action unit's emission by its latent activation makes the rationale faithful by construction, so that ablating an AU removes it from the explanation, a property that transfers to a second language-model backbone, whereas a freely generated rationale is unfaithful.

25.
arXiv (CS.AI) 2026-06-19

Controlled Comparison of Machine Learning Models for Fault Classification and Localization in Power System Protection

arXiv:2510.00831v2 Announce Type: replace Abstract: The increasing complexity of modern power systems, driven by the integration of inverter-based and distributed energy resources, challenges the reliability of conventional protection schemes and motivates the use of machine learning for protection tasks. However, published results are often difficult to compare because datasets, sensing assumptions, and decision horizons vary across studies. This paper presents a controlled comparison of machine learning models for fault classification (FC) and fault localization (FL) under identical sensing, timing, and validation conditions on a common electromagnetic transient dataset, using decision windows of 10-50 ms to reflect protection-relevant time scales. For FC, the best-performing nonlinear models achieve F1 scores above 0.98 already at 10 ms, while lower-capacity models degrade at shorter horizons but improve with longer windows, indicating that relevant fault-type information is already present in the earliest transient. For FL, the top-performing models reach a stable localization error of about 10 % of normalized line length across all evaluated horizons, while weaker models form a clearly separated second performance tier. Line-resolved analysis shows that localization accuracy varies across grid segments, indicating topology-dependent difficulty rather than insufficient temporal context alone. These findings provide a controlled reference for comparing machine learning models across two protection tasks with fundamentally different information requirements.