arXiv preprints from January 1, 2026 through September 21, 2026 — 09:14:20 EST
The BrowseComp-Plus benchmark disentangled the evaluation of agentic search by replacing opaque web search with a fixed corpus, so that an agent's role can be separated from the retriever's. That corpus, however, holds only about 100K documents and was assembled from the supporting documents of the benchmark's own queries plus mined...
Heterogeneous AI systems composed of multiple models, architectures, harnesses, or inference-time settings can improve quality and efficiency by routing queries to the specialist who can answer most effectively at the lowest cost. Routing requires estimating each specialist's expected return, but this value estimation has a cost....
A single training example's contribution to a finished model is normally estimated rather than measured, because measuring it takes two expensive full pre-training runs that differ in one row of one batch. We ran that counterfactual 24 times at a small scale. We trained 32 GPT-2 models at 124M parameters from scratch on OpenWebText,...
We prove matching upper and lower bounds on the space complexity of simulating a large shared register using smaller shared registers. We focus on the case where both the simulated and base registers are single-writer, which means they can be accessed concurrently by multiple readers but only by a single writer. To strengthen our...
ChildSafeAds is a shared task on commercial content in YouTube videos likely to reach children and teenagers. It contains 3,360 videos from 939 channels. Each instance begins with a segment submitted to SponsorBlock, an open-source crowdsourced browser extension whose users mark sponsor segments so that others can skip them. We pair...
As generative AI reshapes professional and educational practice, institutions face a challenge: how to support diverse learners, from non-coders to advanced students, in building confidence and practice with AI-supported problem solving. Most institutional responses bifurcate into conceptual workshops for general audiences or...
Language-model agents can communicate through continuous hidden states that are invisible in public transcripts, creating opportunities for covert harmful coordination. We introduce Verifiable Latent Alignments (VLA), an activation-aware framework for monitoring and steering these private communication channels. For every monitored...
The rapid growth of large data-center (DC) loads is creating new challenges for power-system visibility, privacy, and cyber-physical security. System operators need accurate short-term information about these fast-varying loads, while DC operators may avoid sharing raw megawatt measurements because they can reveal sensitive workload...
We present a nodal discontinuous Galerkin method for solving the Bhatnagar-Gross-Krook (BGK) kinetic equation on multi-dimensional, unstructured grids. The method uses implicit, sweep-based solvers and a moment-preserving projection of the Maxwellian source to enable high-order accuracy in time while avoiding restrictive time steps...
Suppose two parties, Alice and Bob, hold long character strings, $X$ and $Y$, respectively, and they are interested in determining how similar $X$ and $Y$ are. {Moreover, they want to exchange the strings with cost proportional to their degree of dissimilarity.} Such problems arise, for example, in database and file system...
Designing a color palette for data requires designers to balance multiple constraints, including accessibility and aesthetics. Color palette tools support this process through features including direct manipulation, automated palette generation and evaluation, previews, and so on. Despite their prominence, relatively little is known...
Modern Intel AI PCs ship capable integrated GPUs and NPUs with 16+ GB of unified memory, and they spend considerable time idle. That is not enough memory to fit a large model such as a 70B-parameter LLM. We show that a handful of AIPCs, working together over an ordinary network, can serve models beyond the capability of any single...
Bioassay activity prediction is often data-limited because drug-discovery datasets rely on time-consuming and expensive wet-lab experiments for data generation and evaluation. This challenge has inspired recent research into molecular foundation models (MFMs), which aim to encode general-purpose chemical knowledge into molecular...
Spatial aliasing occurs when two or more distinct locations produce highly similar place-cell representations, primarily due to environmental symmetry or repetitive structures. This issue is most pronounced when place representations are constructed solely from boundary vector cell (BVC) inputs, because symmetric or repetitive...
\textbf{Background and Objective}: Reliable atrial fibrillation (AF) detection from electrocardiogram (ECG) signals remains challenging in real-world clinical settings due to variable lead configurations, cross-dataset domain shifts, and pervasive physiological and technical artifacts. So we develop a robust and generalizable deep...
Genomic analysis on viruses such as SARS-CoV-2 variants: Beta, Gamma, Delta, and Omicron is heavily dominated by classical bioinformatics methods, including Sequence Alignment, Phylogenetic Analysis, and Mutation Frequency Statistics. These approaches use pairwise codon or nucleotide distance matrices to analyze gene sequences,...
The European Union has committed to reducing greenhouse gas emissions 55% below 1990 levels by 2030, but whether current trends are compatible with this ambition remains uncertain. We apply deep learning to high-resolution socioeconomic and sectoral data across EU27 member states till 2023 to project sectoral CO$_2$ trajectories under...
Most LLM benchmarks rank models on their ability to automate work tasks. In practice, however, models are often used to assist other (human or LLM) agents. The question that drives model selection is therefore not only which model produces the best output, but which model most improves the work of another (weaker) agent. We introduce...
Quantitative microstructural characterization of Li-ion battery electrode materials using electron backscatter diffraction (EBSD) has been proven as a critical method for optimizing cell performance. However, the inherently slow nature of EBSD can hinder the throughput of analyses needed for statistical representation of a material...
An agent still learning its environment should be cautious while ignorant and bold once confident. The entropic value-at-risk captures this through a robust-optimization identity---a confidence level fixes the radius of a relative-entropy ball of alternative models---but that ball cannot reach catastrophes the nominal deems...
Tabular foundation models (TFMs) achieve strong performance through in-context learning, but context-dependent inference imposes substantial latency and memory costs, hindering large-scale deployment. We propose GEAR (\emph{Generative Expansion and Real Anchoring}), a modular two-stage framework that distills TFMs into lightweight MLP...
Graph neural networks (GNNs) are widely used, but how parameter sparsity affects the expressivity of relational (RGNNs) and temporal (TGNNs) variants is poorly understood. The Strong Expressive Lottery Ticket Hypothesis (SELTH) posits the existence of sparse GNNs that preserve Weisfeiler-Leman (WL) expressivity on static graphs. We...
Researchers often choose a proxy dataset from many releases, transformations, or seeds. Search can make an invalid release appear adequate, while one adequate release does not establish that its generator is reliable. ProxyGuard controls both errors using prespecified bounded risks and a sealed target set. Named-release mode corrects...
This paper proposes a multi-level Bayesian calibration approach that fuses information from heterogeneous sources and accounts for uncertainties in modeling and measurements for time-dependent multi-component systems. The developed methodology has two elements: quantifying the uncertainty at component and system levels, by fusing all...
We study stochastic control of multivariate Hawkes-driven stochastic differential equations with machine learning algorithms in a non-Markovian setting. Due to the path dependence of the memory of the Hawkes intensity, this problem does not fall within classical stochastic control theory outside particular Markovian kernels. We first...