arXiv preprints from January 1, 2026 through July 28, 2026 — 01:12:58 EST
Agentic Retrieval-Augmented Generation (RAG) empowers large language models to autonomously plan and retrieve information for complex problem-solving. However, the development of robust agents is hindered by the scarcity of high-quality training data that reflects the noise and complexity of real-world retrieval environments....
Deep neural networks (DNNs), which support services such as driving assistants and medical diagnoses, undergo lengthy and expensive training procedures. Therefore, the training's outcome - the DNN weights - represents a significant intellectual property asset to protect. Side-channel analysis (SCA) has recently appeared as an...
As generative AI becomes embedded in higher education, it increasingly shapes how students complete academic tasks. While these systems offer efficiency and support, concerns persist regarding over-automation, diminished student agency, and the potential for unreliable or hallucinated outputs. This study conducts a mixed-methods audit...
Currently, the field of structure-based drug design is dominated by three main types of algorithms: search-based algorithms, deep generative models, and reinforcement learning. While existing works have typically focused on comparing models within a single algorithmic category, cross-algorithm comparisons remain scarce. In this paper,...
Neural Combinatorial Optimization (NCO) has mostly focused on learning policies, typically neural networks, that operate on a single candidate solution at a time, either by constructing one from scratch or iteratively improving it. In contrast, decades of work in metaheuristics have shown that maintaining and evolving populations of...
We report the theoretical design and experimental realization of a wideband, all-dielectric mirror that preserves the handedness of incident light upon reflection in the near-infrared range. The mirror consists of a high-contrast, near-subwavelength, one-dimensional dielectric grating on a Bragg mirror. We optimized this structure...
We performed high-precision decay-pion spectroscopy of light $Λ$ hypernuclei at the Mainz Microtron (MAMI) using the A1 spectrometer facility. By measuring the monochromatic $π^-$ momentum from the two-body weak decay $^3_Λ\mathrm{H} \to {}^3\mathrm{He} + π^-$ and referencing it to the $^4_Λ\mathrm{H} \to {}^4\mathrm{He} + π^-$ decay,...
Predicting nationality from personal names has practical value in marketing, demographic research, and genealogical studies. Conventional neural models learn statistical correspondences between names and nationalities from task-specific training data, posing challenges in generalizing to low-frequency nationalities and distinguishing...
JWST observations have suggested that some high-redshift galaxies may be ultra-massive, thereby challenging standard models of early galaxy formation and cosmology. We analyse the stellar masses using different modelling assumptions and with new data of three galaxies (S1, S2 and S3), whose NIRCam/grism redshifts were consistent with...
Context: Traditional software security analysis methods struggle to keep pace with the scale and complexity of modern codebases, requiring intelligent automation to detect, assess, and remediate vulnerabilities more efficiently and accurately. Objective: This paper explores the incorporation of code-specific and general-purpose Large...
Conversational AI is starting to support real clinical work, but most evaluation methods miss how compliance depends on the full course of a conversation. We introduce Obligatory-Information Phase Structured Compliance Evaluation (OIP-SCE), an evaluation method that checks whether every required clinical obligation is met, in the...
Large Language Models (LLMs) have shown strong capabilities across many domains, yet their evaluation in financial quantitative tasks remains fragmented and mostly limited to knowledge-centric question answering. We introduce QuantEval, a benchmark that evaluates LLMs across three essential dimensions of quantitative finance:...
We develop a deformation framework for $C^*$-algebras equipped with a coaction of a locally compact quantum group, formulated intrinsically at the level of spectral subspaces determined by the coaction. The construction is defined algebraically on a finite spectral core and extended by continuity to a natural Fréchet $*$-algebra...
Computational data governance aims to make the enforcement of governance policies and legal obligations more efficient and reliable. Recent advances in natural language processing and agentic AI offer ways to improve how organizations share and use data. But many barriers remain. Today's tools require technical skills and multiple...
Computing functional determinants of differential operators is central to any field-theoretical calculation relying on a saddle-point expansion. A variety of approaches is available for the computation that avoid having to know the eigenspectrum of the operator, and in particular the Gel'fand-Yaglom theorem and the Green's function...
We discuss the role of quantum reference frames in providing a viable definition of rest frame for mixed particles. We then analyze the related concept of frame-dependent entanglement and its impact on the phenomenology of neutral mesons and neutrinos.
Many areas in science and engineering now have access to technologies that enable the rapid collection of overwhelming data volumes. While these datasets are vital for understanding phenomena from physical to biological and social systems, the sheer magnitude of the data makes even simple storage, transmission, and basic processing...
Women are twice as likely as men to face online harassment due to their gender. Despite recent advances in multimodal content moderation, most approaches still overlook the social dynamics behind this phenomenon, where perpetrators reinforce prejudices and group identity within like-minded communities. Graph-based methods offer a...
In antiquity, the seal embodied trust, secrecy, and integrity in safeguarding the exchange of letters and messages. The purpose of this work is to continue this tradition in the contemporary era, characterized by the presence of quantum computers, classical supercomputers, and increasingly sophisticated artificial intelligence. We...
Thoracic aortic dissection and aneurysms are the most lethal diseases of the aorta. The major hindrance to treatment lies in the accurate analysis of the medical images. More particularly, aortic segmentation of the 3D image is often tedious and difficult. Deep-learning-based segmentation models are an ideal solution, but their...
Summarization of multi-party dialogues is a critical capability in industry, enhancing knowledge transfer and operational effectiveness across many domains. However, automatically generating high-quality summaries is challenging, as the ideal summary must satisfy a set of complex, multi-faceted requirements. While summarization has...
The BESIII experiment has collected 2.6 billion $ψ(3686)$ events, 10 billion events, 20 $fb^{-1}$ of $D$ meson pairs at 3.773 GeV, and 7.33 $fb^{-1}$ of $D_sD_s^*$ events from 4.128 to 4.226 GeV. These huge data samples allow us to search for rare or forbidden processes in charm hadron decays. We summarize the recent research of charm...
Detector visualization plays a vital role in high energy physics (HEP) experiments, yet existing detector descriptions, such as GDML, lack compatibility with industrial 3D tools. We present an automated conversion framework that transforms four major HEP detector descriptions, including GDML, Geant4, ROOT and DD4hep, into standardized...
As users increasingly expect LLMs to align with their preferences, personalized information becomes valuable. However, personalized information can be a double-edged sword: it can improve interaction but may compromise objectivity and factual correctness, especially when it is misaligned with the question. To alleviate this problem,...
Let $\mathcal{D}$ be a block design admitting a locally transitive automorphism group $G$. We say that $\mathcal{D}$ is $G$-point-locally dihedral if the induced local action $G_x^{\mathcal{D}}$ is dihedral for each point $x$, and that $\mathcal{D}$ is $G$-block-locally dihedral if the induced local action $G_B^B$ is dihedral for each...