×

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: Chen ×
换一批
01.
medRxiv (Medicine) 2026-06-22

Repeat expansions in Parkinson's disease and parkinsonism across ancestries: insights from a global genetic cohort

Expanded short tandem repeats contribute to a broad spectrum of neurodegenerative diseases, yet their roles in Parkinson's disease (PD) and parkinsonism remain incompletely characterized, especially across diverse ancestries. We analyzed short-read whole-genome (WGS) and clinical exome sequencing (CES) data from 38,365 individuals (28,861 WGS; 9,504 CES), encompassing 23,242 patients with PD, 4,729 patients with atypical parkinsonism and 10,394 healthy controls from 11 genetic ancestries. To determine carrier frequencies and characterize repeat structures across diverse ancestries, we genotyped 12 established pathogenic loci where normal, intermediate, and pathogenic alleles can be reliably differentiated using short-read sequencing data. Additionally, we conducted threshold-based associations to determine the minimum threshold associated with increased PD risk in 15,995 individuals (8,591 PD, 7,404 controls) of European ancestry. Pathogenic repeat expansions were detected in 62 patients (56 PD and 6 atypical parkinsonism) and 5 controls across seven loci (AR, ATXN1, ATXN2, ATXN3, CACNA1A, HTT and THAP11), spanning seven ancestries. Among these, ATXN2 expansions were the most frequently observed in PD and were present in African, East Asian, European and Middle Eastern ancestries. Additionally, intermediate ATXN2 repeat expansions exhibited a strong, length-dependent association with PD risk in the European population, with individuals with [≥]32 repeats having a more than four-fold increased risk (odds ratio 4.25, 95% confidence interval 1.80-12.05). Overall, >92% of expanded alleles harbor CAA interruptions within the CAG tract. Pathogenic expansions at other loci, such as ATXN3 and THAP11, showed more ancestry-specific distributions. Clinically, individuals with pathogenic ATXN2 and ATXN3 expansions most often presented with typical PD features but frequently showed earlier disease onset and a strong family history of PD. This large-scale, multi-ancestry study comprehensively maps the genetic landscape of pathogenic and intermediate repeat expansions in PD. Our findings confirm a length- and structure-dependent risk association for ATXN2 with PD in the European population, and highlight the pleiotropic effects of repeat expansions across the parkinsonian spectrum.

02.
arXiv (CS.AI) 2026-06-16

Towards Verifiable Agentic Data Science: Solving Irregular TSQA Via Tool-Grounded Reasoning

arXiv:2606.15107v1 Announce Type: new Abstract: Time series data in real-world deployments is overwhelmingly irregular. Observations are asynchronous, missing values are informative rather than random, and sampling frequencies vary across sensors and operational windows. However, existing Time Series Question Answering (TSQA) benchmarks mostly assume regularly sampled inputs, leaving a fundamental gap in understanding how large language models (LLMs) and AI agents perform under irregular conditions. To bridge this gap, we introduce IRTS-ToolBench, a benchmark of 1,700 questions spanning 10 task types across 13 domains. IRTS-ToolBench is designed to be used independently by any researcher working on LLM-based irregular time series analysis, providing standardized inputs and a reproducible evaluation protocol. Code can be found in https://github.com/SanhornC/IRTS-ToolBench.

03.
arXiv (CS.CV) 2026-06-12

DIMOS: Disentangling Instance-level Moving Object Segmentation

Moving instance segmentation (MIS) attracts increasing attention due to its broad applications in traffic surveillance, autonomous driving, and animal tracking. Event cameras record asynchronous brightness changes, providing high temporal resolution and dynamic range, which makes them highly sensitive to motion information. By fusing event and image features, motion cues from events can complement spatial details from images, enhancing the performance of MIS. However, current multimodal MIS methods still struggle to segment small moving instances, as event cameras often yield sparse features under limited resolution. Moreover, event features entangle appearance attributes with motion cues, which further restricts effective cross-modal fusion. To address these challenges, we first propose a dual-disentangling feature extraction framework that separates and extracts appearance and motion information within both image and event modalities, thereby improving feature density. Subsequently, a multi-granularity cross-modal alignment is introduced to align distributionally and semantically consistent features across modalities, enabling more effective fusion with rich spatial and temporal details. The experiment results demonstrate that our method achieves state-of-the-art performance in multimodal MIS, especially for small instances under challenging conditions such as fast motion and low-light settings.

04.
arXiv (CS.CL) 2026-06-18

BCL: Bayesian In-Context Learning Framework for Information Extraction

Existing information extraction (IE) tasks increasingly adopt in-context learning (ICL) with large language models. However, current approaches either show inconsistent performance across model scales or lack systematic optimization and generalizability. Building on this, we propose BCL (Bayesian In-Context Learning Framework for Information Extraction), the first optimization framework that uses particle filtering with Bayesian updates to systematically refine label representations across IE tasks. Through four steps initialization, observation, weight update, and resampling, BCL generalizes to both sequence labeling and relation classification paradigms. Extensive experiments demonstrate substantial and consistent improvements over existing approaches.

05.
arXiv (CS.CL) 2026-06-18

Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads

While large language models (LLMs) have become highly capable, they remain prone to factual inaccuracies, commonly referred to as "hallucinations." Uncertainty quantification (UQ) offers a promising way to mitigate this issue, but most existing methods are computationally intensive and/or require supervision. In this work, we propose Recurrent Attention-based Uncertainty Quantification (RAUQ), an unsupervised and efficient framework for identifying hallucinations. The method leverages an observation about transformer attention behavior: when incorrect information is generated, certain "uncertainty-aware" attention heads tend to reduce their focus on preceding tokens. RAUQ automatically detects these attention heads and combines their activation patterns with token-level confidence measures in a recurrent scheme, producing a sequence-level uncertainty estimate in just a single forward pass. Through experiments on twelve datasets spanning question answering, summarization, and translation across nine different LLMs, we show that RAUQ consistently outperforms state-of-the-art UQ baselines. Importantly, it incurs minimal overhead, requiring less than 1\% additional computation. Since it requires neither labeled data nor extensive parameter tuning, RAUQ serves as a lightweight, plug-and-play solution for real-time hallucination detection in white-box LLMs.

06.
arXiv (CS.LG) 2026-06-18

KEPLA: A Knowledge-Enhanced Deep Learning Framework for Accurate Protein-Ligand Binding Affinity Prediction

arXiv:2506.13196v5 Announce Type: replace Abstract: Accurate prediction of protein-ligand binding affinity is critical for drug discovery. While recent deep learning approaches have demonstrated promising results, they often rely solely on structural features of proteins and ligands, overlooking their valuable biochemical knowledge associated with binding affinity. To address this limitation, we propose KEPLA, a novel deep learning framework that explicitly integrates prior knowledge from Gene Ontology and ligand properties to enhance prediction performance. KEPLA takes protein sequences and ligand molecular graphs as input and optimizes two complementary objectives: (1) aligning global representations with knowledge graph relations to capture domain-specific biochemical insights, and (2) leveraging cross attention between local representations to construct fine-grained joint embeddings for prediction. Experiments on two benchmark datasets across both in-domain and cross-domain scenarios demonstrate that KEPLA consistently outperforms state-of-the-art baselines. Furthermore, interpretability analyses based on knowledge graph relations and cross attention maps provide valuable insights into the underlying predictive mechanisms.

07.
arXiv (CS.LG) 2026-06-11

Learning Patterns and Abstractions from Perceptual Sequences

作者:

arXiv:2503.10973v2 Announce Type: replace Abstract: Cognition swiftly breaks high-dimensional sensory streams into familiar parts and uncovers their relations. Why do structures emerge, and how do they enable learning, generalization, and prediction? What computational principles underlie this core aspect of perception and intelligence? A sensory stream, simplified, is a one-dimensional sequence. In learning such sequences, we naturally segment them into parts – a process known as chunking. In the first project, I investigated factors influencing chunking in a serial reaction time task and showed that humans adapt to underlying chunks while balancing speed and accuracy. Building on this, I developed models that learn chunks and parse sequences chunk by chunk. Normatively, I proposed chunking as a rational strategy for discovering recurring patterns and nested hierarchies, enabling efficient sequence factorization. Learned chunks serve as reusable primitives for transfer, composition, and mental simulation – letting the model compose the new from the known. I demonstrated this model's ability to learn hierarchies in single and multi-dimensional sequences and highlighted its utility for unsupervised pattern discovery. The second part moves from concrete to abstract sequences. I taxonomized abstract motifs and examined their role in sequence memory. Behavioral evidence suggests that humans exploit pattern redundancies for compression and transfer. I proposed a non-parametric hierarchical variable model that learns both chunks and abstract variables, uncovering invariant symbolic patterns. I showed its similarity to human learning and compared it to large language models. Taken together, this thesis suggests that chunking and abstraction as simple computational principles enable structured knowledge acquisition in hierarchically organized sequences, from simple to complex, concrete to abstract.

08.
arXiv (CS.AI) 2026-06-12

CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction

arXiv:2603.00610v3 Announce Type: replace-cross Abstract: While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind. In this paper, we bridge this critical gap by establishing a comprehensive ecosystem for music reward modeling under Compositional Multimodal Instruction (CMI), where the generated music may be conditioned on text descriptions, lyrics, and audio prompts. We first introduce CMI-Pref-Pseudo, a large-scale preference dataset comprising 110k pseudo-labeled samples, and CMI-Pref, a high-quality, human-annotated corpus tailored for fine-grained alignment tasks. To unify the evaluation landscape, we propose CMI-RewardBench, a unified benchmark that evaluates music reward models on heterogeneous samples across musicality, text-music alignment, and compositional instruction alignment. Leveraging these resources, we develop CMI reward models (CMI-RMs), a parameter-efficient reward model family capable of processing heterogeneous inputs. We evaluate their correlation with human judgment scores on musicality and alignment on CMI-Pref along with previous datasets. Further experiments demonstrate that CMI-RM not only correlates strongly with human judgments, but also enables effective inference-time scaling via top-k filtering. Code is available at GitHub (https://github.com/Haiwen-Xia/CMI-RewardBench). Model weights: CMI-RM (https://huggingface.co/HaiwenXia/CMI-RM). Datasets: CMI-Pref-Pseudo (https://huggingface.co/datasets/HaiwenXia/cmi-pref-pseudo) and CMI-Pref (https://huggingface.co/datasets/HaiwenXia/cmi-pref)

09.
arXiv (CS.LG) 2026-06-18

JourneyFormer: Encoding Airbnb Guest Journey with Sequence Modeling

arXiv:2606.19108v1 Announce Type: new Abstract: Sequence modeling has become increasingly popular in recommendation and ranking algorithms, owing to its capacity to model users' historical behaviors and infer user intentions. Despite its theoretical simplicity, the practical deployment of a sequence model in production is non-trivial due to complexity of the sequence and sparse labels. For example, in Airbnb, guest sequences are often long, exploratory and complex, and we focus on booking labels, which are sparse. As such, we are often required to make various design decisions regarding data and modeling to strike a balance between effectiveness and scalability. This work delved into these production challenges and deployed JourneyFormer, a sequence modeling solution for search ranking at Airbnb. We detail crucial design considerations, covering aspects such as guest event selection, ID embeddings, model architecture, and label attribution. Additionally, we describe several tailored strategies to accelerate model training and inference. JourneyFormer has been successfully deployed within Airbnb's production, where its effectiveness and impact have been evidenced not only by improved offline ranking metrics but also by significant gains in key business metrics through online A/B testing across 2 production surfaces.

10.
arXiv (CS.CV) 2026-06-19

WeGenBench: A Multidimensional Diagnostic Benchmark towards Text-to-Image Model Optimization

Recent text-to-image generation models have demonstrated remarkable capabilities in synthesizing highly realistic images from text inputs alone. Although existing benchmarks can evaluate the generation capabilities of various models to some extent, they struggle to comprehensively and accurately measure performance across multiple dimensions, often failing to reveal the inherent deficiencies of models in specific categories. To address these limitations, we propose WeGenBench, a novel benchmark designed for the comprehensive, multi-perspective evaluation of text-to-image generation capabilities. Our benchmark comprises a total of 4,000 test prompts across two primary categories, meticulously balanced between Chinese and English to evaluate bilingual and cross-cultural generation capabilities. Beyond macroscopic scene classification, we annotate each prompt with multi-dimensional tags tailored to the distinct content and challenges of each language, thereby refining the generation tasks into more specific sub-categories. Through a cross-dimensional evaluation mechanism leveraging both scene classifications and multi-dimensional tags, WeGenBench can precisely pinpoint model shortcomings in specific generation categories. Furthermore, to measure generation quality more accurately, we design and validate several novel evaluation metrics by integrating Vision-Language Models (VLMs), which assess model performance on domain-specific tasks from three core aspects. Crucially, our approach yields both the assessment outcomes and the detailed reasoning trajectories, facilitating a rigorous verification of the accuracy and soundness of the evaluation results. Finally, we conduct systematic benchmarking on current state-of-the-art methods and provide an in-depth analysis of the limitations present in existing models.

11.
arXiv (CS.CL) 2026-06-16

How Much Can We Trust LLM Search Agents? Measuring Endorsement Vulnerability to Web Content Manipulation

Large language model (LLM)-based search agents synthesize open-web content into actionable recommendations on behalf of users, creating a risk that attacker-published pages are transformed into endorsed claims. We introduce SearchGEO, a controlled evaluation framework for measuring endorsement corruption in LLM-based web-search agents, combining a web-evidence manipulation pipeline, a five-mode attack taxonomy, and multiple output-level metrics. We evaluate 13 LLM backends on 308 cases each. Results show that vulnerability patterns vary across backends: overall attack success rate (ASR) ranges from 0.0% on Claude-Sonnet-4.6 to 31.4% on Gemini-3-Flash, the strongest attack mode differs by model family, and the same deployment scaffold could amplify or decrease ASR on different backends. An auxiliary agent-skill probe, where endorsement becomes an install command, exposes a sharp split among otherwise robust backends: Claude over-rejects while GPT over-trusts. These findings argue for treating recommendation reliability under adversarial search content as a first-class dimension of backend safety evaluation.

12.
medRxiv (Medicine) 2026-06-22

Artificial Intelligence-Enabled Cardiac Function Estimation from Phone Videos of Echocardiograms

Importance: Mobile phone-recorded echocardiogram videos are commonly used in point of care, telemedicine, and resource-limited workflows, but artificial intelligence models for left ventricular ejection fraction (LVEF) estimation have primarily been evaluated on native Digital Imaging and Communications in Medicine (DICOM) videos. Objective: To evaluate whether previously described artificial intelligence models for LVEF estimation retain performance when applied to mobile phone-recorded echocardiographic videos. Design: Multicenter model validation study comparing model-estimated LVEF with clinician reported LVEF. Setting: Three medical centers: Kaiser Permanente Northern California, Beth Israel Deaconess Medical Center through MIMIC-IV-ECHO, and Cedars-Sinai Medical Center. Participants: Source studies with clinician reported LVEF and apical 4-chamber or apical 2-chamber views, yielding 6209 phone-recorded videos from 2648 studies and 2611 patients. Exposures: Mobile phone recording of native echocardiographic videos and fine-tuning of pretrained models using mobile phone-recorded videos from the Kaiser Permanente Northern California training cohort. Main Outcomes and Measures: Mean absolute error in ejection fraction percentage points, R^2 for continuous estimation, and area under the receiver operating characteristic curve for identifying ejection fraction greater than 50%. Results: The study included 6209 mobile phone recorded echocardiographic videos from 2648 studies and 2611 patients; the weighted mean age was 68.4 years, and 1031 patients were male (39.5%). Without phone-video fine-tuning, the primary model achieved a mean absolute error of 7.00 percentage points, coefficient of determination of 0.49, and area under the receiver operating characteristic curve of 0.91 on phone-recorded videos; corresponding native DICOM performance was 6.08 percentage points, 0.60, and 0.93, respectively. On the 2396-video fine-tuning evaluation cohort, fine-tuning improved primary model performance to a mean absolute error of 6.96 percentage points, coefficient of determination of 0.61, and area under the receiver operating characteristic curve of 0.93. Fine-tuning the public EchoNet-Dynamic model improved performance from 9.36 percentage points, 0.37, and 0.84 to 7.86 percentage points, 0.50, and 0.89, respectively. Progressive central zoom preprocessing degraded model performance. Conclusions and Relevance: These findings suggest that artificial intelligence assisted left ventricular ejection fraction estimation from mobile phone-recorded echocardiograms may be feasible when native image export is unavailable, although prospective evaluation is needed before clinical deployment.

13.
arXiv (CS.AI) 2026-06-11

APPO: Agentic Procedural Policy Optimization

arXiv:2606.12384v1 Announce Type: cross Abstract: Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn tool-use capabilities of large language model agents. However, most existing methods assign credit over coarse heuristic units, such as tool-call boundaries or fixed workflows, making it difficult to identify which intermediate decisions influence downstream outcomes. In this work, we study agentic RL from two perspectives: where to branch and how to assign credit after branching. Our pilot analysis shows that influential decision points are broadly distributed throughout the generated sequence rather than concentrated at tool calls, while token entropy alone does not reliably reflect their impact on final outcomes. Motivated by these observations, we propose Agentic Procedural Policy Optimization (APPO), which shifts branching and credit assignment from coarse interaction units to fine-grained decision points in the sequence. APPO selects branching locations using a Branching Score that combines token uncertainty with policy-induced likelihood gains of subsequent continuations, enabling more targeted exploration while filtering out spurious high-entropy positions. It further introduces procedure-level advantage scaling to better distribute credit across branched rollouts. Experiments on 13 benchmarks show that APPO consistently improves strong agentic RL baselines by nearly 4 points, while keeping efficient tool-calls and maintaining behavior interpretability.

14.
bioRxiv (Bioinfo) 2026-06-22

EMAlign: accurate alignment of cryo-EM maps through main-chain probability using deep learning

Accurate alignment of cryo-EM density maps is essential for comparing conformational states, searching map libraries, and guiding atomic model building, but remains challenging for noisy experimental maps and partially overlapping structures. Existing alignment methods are often based on raw maps, which may result in reduced accuracy due to the density noise, or require manual intervention for local alignment, which suffers from limited general applicability. Addressing the limitations, we present EMAlign, an automatic global and local cryo-EM map alignment with predicted main-chain probability using deep learning. First, EMAlign predicts main-chain prob ability maps from raw cryo-EM density maps using a BiMCUNet network. Then, a fast Fourier transform (FFT)-based search strategy is used to globally search the accurate alignment between cryo-EM maps based on predicted main-chain probability maps. As such, the main-chain prob ability map overcomes the noisy raw map problem, and the FFT-based exhaustive global search ensures the general applicability of alignment. EMAlign is evaluated on 64 global map pairs, 195 local map pairs, and 60 structure-to-map pairs at 3-10 [A] resolution and compared with gmfit, fitmap, VESPER, and CryoAlign. It is shown that EMAlign outperforms the other methods in both global and local alignment, achieving mean RMSDs of 1.03 [A] (global), 2.56 [A] (local), and 0.82 [A] (structure-to-map), with success rates of 100.0%, 100.0%, and 98.3% under the criterion of RMSD < 10 [A]. The EMAlign package is freely available at https://github.com/huang-laboratory/EMAlign/.

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

CacheRL:Multi-Turn Tool-Calling Agents via Cached Rollouts and Hybrid Reward

We present CacheRL, a system for training small agent foundation models that achieves 92 percent process accuracy on multi-step tool-calling tasks, approaching GPT-5's 94 percent while requiring 100 times less compute. Our approach addresses three challenges in practical agent training: transferring tool-calling knowledge from large models at scale, enabling reinforcement learning without costly live tool execution, and learning robustly from noisy cached environments. CacheRL introduces three key innovations. First, a hybrid thinking trajectory pipeline augments agent trajectories with LLM-generated reasoning traces, producing training examples that teach models not only what tools to call but also why. Second, the CacheAgentLoop eliminates live execution costs through a three-tier fuzzy cache while preserving trajectory fidelity using token-level masking. Third, a cache-tier-aware reward dynamically adjusts answer-quality weights to avoid penalizing models for cache-induced limitations. Through iterative supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO), CacheRL improves Qwen3-4B-Thinking's validation reward from 0.43 to 0.78. On public agentic tool-calling benchmarks, our model achieves competitive performance against frontier models such as GPT-5. Ablation studies show that removing knowledge transfer reduces performance by 41 percent, while cache-aware rewards contribute a 17 percent improvement. Interestingly, reinforcement learning improves training stability but yields limited gains beyond strong supervised fine-tuning, suggesting that data quality and reward design play a more important role than complex optimization methods in building practical small agent models.

16.
medRxiv (Medicine) 2026-06-23

Association between the hemoglobin albumin lymphocyte and platelet score and chronic kidney disease: insights from patient data and animal models

Introduction The hemoglobin, albumin, lymphocytes and platelets (HALP) score, a novel nutritional and inflammatory biomarker, has been used in various chronic disease studies. However, the relationship between the HALP score and chronic kidney disease (CKD) remains poorly elucidated. This study aimed to explore the possible association between the HALP score and CKD. Methods Our analysis encompassed 25,160 adult participants drawn from NHANES cycles spanning 2009 through 2018. Weighted multivariable logistic regression and generalized additive models (GAMs) were employed to evaluate the independent associations between the HALP score and CKD, albuminuria, and low-estimated glomerular filtration rate (eGFR). Threshold effects were examined using two-piecewise linear regression. Subgroup and sensitivity analyses were performed to assess robustness. Receiver operating characteristic (ROC) curve analyses were applied to compare the discriminative capacity of the HALP score with the prognostic nutritional index (PNI), systemic immune-inflammation index (SII), lymphocyte-to-monocyte ratio (LMR), and platelet-to-lymphocyte ratio (PLR). The clinical findings were further validated in a 5/6 nephrectomy rat model. Results After adjustment for multiple confounders, higher HALP scores were inversely associated with the risk of CKD (OR = 0.97, 95% CI: 0.94-0.99) and albuminuria (OR = 0.97, 95% CI: 0.93-0.99). However, after full adjustment for demographic characteristics, physical examination indices and laboratory parameters (Model 3), the correlation between the HALP score and low-eGFR was no longer statistically significant. Non-linear analyses revealed a threshold effect, with CKD risk declining as the HALP score increased up to an inflection point of 52.43 (OR = 0.97, 95% CI: 0.95-0.99), beyond which no further protective effect was observed. A similar threshold effect was identified for albuminuria. Subgroup and interaction analyses indicated no meaningful effect modification by age, sex, BMI, hypertension, or diabetes. Sensitivity analyses confirmed the robustness of the results. ROC analysis demonstrated that the HALP score showed superior discriminative ability for CKD and albuminuria compared with PNI, SII, LMR, and PLR. In the animal experiment, CKD model rats exhibited significantly lower HALP scores than controls. Inverse correlations were observed between the HALP score and serum creatinine (Scr), blood urea nitrogen (BUN), and urinary albumin-to-creatinine ratio (UACR), with UACR showing the strongest correlation, which was consistent with the clinical findings. Conclusion Lower HALP scores are independently associated with increased prevalence of CKD and albuminuria. As an affordable and readily measurable biomarker, the HALP score may facilitate CKD risk assessment.

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

Beyond Monolingual Deep Research: Evaluating Agents and Retrievers with Cross-Lingual BrowseComp-Plus

Deep research agents are increasingly evaluated on their ability to search for evidence, reason over retrieved sources, and produce grounded answers. Existing browsing benchmarks, however, largely assume that the user's query and the supporting evidence are written in the same language, leaving open whether agentic search systems can operate when relevant evidence appears in another language. We introduce XBCP (Cross-lingual BrowseComp-Plus), a controlled benchmark that preserves the English question-and-answer space of BrowseComp-Plus but varies the languages of the supporting documents. XBCP instantiates two complementary settings: in the cross-lingual setting, each query is paired with evidence in a single assigned language. In the multilingual setting, the full evidence corpus is distributed equally and randomly across 12 languages spanning high-resource and low-resource regimes. We evaluate four deep research agents using sparse and dense multilingual retrievers, measuring answer accuracy, evidence recall, search behavior, calibration, citation fidelity, and oracle retrieval. Results reveal substantial degradation when evidence is translated. Even strong, dense retrievers lose evidence recall, and agents become less calibrated and cite evidence less reliably. Notably, accuracy remains lower even when all gold evidence is supplied directly. These findings suggest that cross-lingual deep research exposes both retrieval failures and an independent, agent-side difficulty in integrating language-mismatched evidence.

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

CEO-Bench: Can Agents Play the Long Game?

Language model agents are becoming proficient executors at isolated, short-horizon tasks such as software engineering and customer service. Yet real-world challenges require a combination of sophisticated skills that remain largely untested in agents: (1) navigating long horizons amid uncertainty; (2) acquiring information in noisy environments; (3) adapting to a changing world; (4) orchestrating multiple moving parts toward a coherent goal. We introduce CEO-Bench, which evaluates these capabilities together by simulating a representative real-world task: operating a startup for 500 days. An agent manages pricing, marketing, budgeting, and many other aspects of a fictional company through a programmable Python interface, operating in the same environment and facing the same challenges as a human CEO. Success demands analyzing noisy, interconnected business databases, translating signals into sound strategy, and coordinating many decisions with programming. The strongest agents write sophisticated code that simulates customer cohorts to forecast future cash and mines negotiation history to uncover hidden customer preferences. Even so, most state-of-the-art models struggle in this environment. Only Claude Opus 4.8 and GPT-5.5 finish above the $1M starting balance, and neither consistently turns a profit. CEO-Bench takes a first step toward measuring the intelligence required to drive sustained, adaptive progress over time.

19.
arXiv (CS.CV) 2026-06-12

Multi-Label Test-Time Adaptation with Bayesian Conditional Priors

Multi-label recognition with frozen Vision-Language Models (VLMs) is brittle under distribution shift: standard zero-shot inference scores labels independently, ignoring co-occurrence structure and producing incoherent label sets where dominant concepts suppress weaker but compatible labels. We introduce Bayesian Conditional Priors (BCP) Estimation, a gradient-free test-time adaptation method that injects label dependency without tuning the backbone. BCP views zero-shot logits as a proxy for marginal posteriors under a fixed image-text likelihood and attributes shift-induced errors mainly to a mismatched label prior. For each test image, it selects a high-confidence anchor label and applies an anchor-conditioned Bayesian refinement. This update is closed-form in logit space and admits a pointwise mutual information (PMI) interpretation, explicitly promoting compatible labels and suppressing incompatible ones. BCP operates without target annotations by estimating anchor-conditioned priors online from the unlabeled test stream via lightweight second-order co-occurrence statistics, adding negligible overhead beyond a single forward pass. Across standard multi-label benchmarks and multiple CLIP backbones, BCP consistently outperforms strong TTA baselines, e.g., improving RN50 average mAP from 57.31 to 69.22 and ViT-B/16 from 62.61 to 71.79.

20.
arXiv (CS.CV) 2026-06-16

Towards Next-Generation Healthcare: A Survey of Medical Embodied AI for Perception, Decision-Making, and Action

Foundation models have demonstrated impressive performance in enhancing healthcare efficiency across a wide range of medical applications. Nevertheless, their limited ability to perceive, understand, and interact with the physical world significantly constrains their effectiveness in real-world clinical workflows, where safety-critical decision-making and physical execution are tightly coupled. Recently, embodied artificial intelligence (AI) has emerged as a promising physical-interactive paradigm for intelligent healthcare, enabling agents to operate in complex medical environments. As research in this area rapidly expands, understanding how intelligent agents function as integrated, end-to-end systems in clinical environments becomes increasingly critical. However, existing surveys on medical embodied AI largely emphasize individual aspects or functional components, lacking a unified system-level organization of the field. To support and consolidate recent advances, we systematically survey the core components of medical embodied AI, with a particular emphasis on the coordinated integration of perception, decision-making, and action. We further review representative medical applications and relevant datasets, and we analyze the major challenges encountered in real-world clinical practice. Finally, we discuss key directions for future research in this rapidly evolving field. The associated project can be found at https://github.com/VMVLab/Medical_Embodied_AI_Paper_List.

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

ACCORD: Action-Conditioned Contextual Grounding for Language Agents

User instructions are often underspecified because humans rely on implicit assumptions about the surrounding environment. For large language model (LLM) agents operating in information-rich digital and physical environments, these assumptions cannot be inferred from the instruction alone; they must be recovered from the current state of tools, data, interfaces, and observations. Effective execution therefore requires agents to identify missing context, ground it in observed evidence, and carry it forward into subsequent actions. We show that current agents often fail to do so. They act from assumed rather than observed specifics, overlook information they could have gathered, and fail to incorporate evidence that has already been returned. Building on this insight, we propose ACCORD (Action-Conditioned Contextual Grounding), a simple and effective agent framework for adaptive grounding. Before each action, ACCORD actively probes the environment for missing information and integrates relevant context from the agent's trajectory that would otherwise be overlooked. Requiring no additional training or task-success signals, ACCORD improves task-goal completion on AppWorld by up to +20.6 points with GPT-5-mini, from 42.0% to 62.6%, compared to strong baselines. These gains persist with a substantially stronger base model (+10.8 with Claude-4.5-sonnet), an open-weight model (+10.1 with Qwen3.5-27B-FP8), and on the embodied AlfWorld benchmark (+7.4 success rate with GPT-5-mini).

22.
arXiv (CS.LG) 2026-06-16

Beyond the Blood Draw: Explainable Machine Learning for Non-Invasive Dysglycemia Risk Screening

arXiv:2606.16056v1 Announce Type: new Abstract: Dysglycemia, encompassing both prediabetes and diabetes, affects huge numbers of adults worldwide, yet many of them remain undiagnosed. We developed and validated machine-learning (ML) models for non-invasive screening of dysglycemia risk that require no laboratory tests. Pooling data from the National Health and Nutrition Examination Survey (NHANES) 2017–2023 (n=14,352), we trained six ML models with stratified 5-fold cross-validation and compared them with two established clinical risk scores. LightGBM achieved the highest area under the receiver operating characteristic curve (AUC=0.820, 95% CI: 0.806–0.835), outperforming the Finnish Diabetes Risk Score (0.745) and American Diabetes Association Risk Test (0.783). SHAP analysis identified age, race/ethnicity, and waist-to-height ratio as the most influential predictors. Subgroup analyses confirmed consistent performance across demographic strata (AUC: 0.735–0.832). These results demonstrate the feasibility of explainable, laboratory-free dysglycemia screening for deployment in community settings and self-tracking health applications.

23.
arXiv (CS.LG) 2026-06-12

Central Limit Theorems for Stochastic Gradient Descent Quantile Estimators

arXiv:2503.02178v3 Announce Type: replace-cross Abstract: This paper develops asymptotic theory for quantile estimation via stochastic gradient descent (SGD) with a constant learning rate. The quantile loss function is neither smooth nor strongly convex. Beyond conventional perspectives and techniques, we view quantile SGD iteration as an irreducible, periodic, and positive recurrent Markov chain, which cyclically converges to its unique stationary distribution regardless of the arbitrarily fixed initialization. To derive the exact form of the stationary distribution, we analyze the structure of its characteristic function by exploiting the stationary equation. We also derive tight bounds for its moment generating function (MGF) and tail probabilities. Synthesizing the aforementioned approaches, we prove that the centered and standardized stationary distribution converges to a Gaussian distribution as the learning rate $\eta\rightarrow0$. This finding provides the first central limit theorem (CLT)-type theoretical guarantees for the quantile SGD estimator with constant learning rates. We further propose a recursive algorithm to construct confidence intervals of the estimators with statistical guarantees. Numerical studies demonstrate the effective finite-sample performance of the online estimator and inference procedure. The theoretical tools developed in this study are of independent interest for investigating general SGD algorithms formulated as Markov chains, particularly in non-strongly convex and non-smooth settings.

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

QuantKAN: A Unified Quantization Framework for Kolmogorov Arnold Networks

arXiv:2511.18689v3 Announce Type: replace Abstract: Kolmogorov–Arnold Networks (KANs) replace linear weights with spline-based functions, offering strong expressivity but posing challenges for low-precision deployment due to heterogeneous parameter distributions. We introduce QuantKAN, the first unified framework for quantization-aware training (QAT) and post-training quantization (PTQ) of KANs. The framework employs branch-aware quantizers for base and spline parameters and extends modern QAT and PTQ methods to spline-based layers across EfficientKAN, FastKAN, PyKAN, and KAGN. Experiments on MNIST, CIFAR-10/100, TinyImageNet, and ImageNet provide the first unified QAT/PTQ KAN benchmarks and show that DSQ is the most robust QAT method at aggressive low-bit settings, while GPTQ is the strongest PTQ method at moderate precision. Sensitivity analyses reveal architecture-specific failure modes: spline/basis parameters dominate in FastKAN, while base or scaling parameters dominate in EfficientKAN, GRAM, and PyKAN. Vivado HLS estimates on a Xilinx UltraScale+ device further suggest up to 3.32$\times$ throughput and 7.7$\times$ lower estimated dynamic energy per inference under W4A4, exposing a residual basis-evaluation tax that motivates basis-aware microarchitecture. QuantKAN is available at https://github.com/OSU-STARLAB/QuantKAN/.

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

NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics

Physics-grounded video generation requires controllable 3D object dynamics that remain physically consistent under contact, deformation, and external forcing. Existing trajectory-based methods often model isolated physical effects, making it difficult to compose conservative and non-conservative dynamics in contact-rich 3D scenes. We present NEXUS, a neural energy-field framework for contact-rich 3D object dynamics. NEXUS represents each object as a structural graph and constructs dynamic object-object and object-environment contact graphs. Inspired by Hamiltonian Neural Networks, NEXUS formulates motion through scalar energy and dissipation terms rather than directly predicting states or accelerations. Conservative effects, including gravity and elastic deformation, are composed as additive energy terms, while non-conservative effects such as damping and impact-induced energy loss are modeled with learned Rayleigh-style dissipation. Forces are derived by differentiating the energy and dissipation functions and rolled out with a multi-substep semi-implicit integrator. Across controlled trajectory benchmarks, NEXUS improves long-horizon accuracy over representative learned and physics-structured dynamics baselines under varying mechanical properties and physical-effect compositions. We further show that NEXUS trajectories provide effective guidance for contact-rich video generation, improving physical plausibility while maintaining competitive visual quality.