arXiv preprints from January 1, 2026 through September 12, 2026 — 09:37:50 EST
Tool calling allows large language models (LLMs) to interact with external systems like APIs, enabling applications in customer support, data analysis, and dynamic content generation. While recent benchmarks have advanced tool-use research, they suffer from key limitations, including reliance on simulated or restricted APIs, limited...
Audio processing methods based on deep neural networks are typically trained at a single sampling frequency (SF). To handle untrained SFs, signal resampling is commonly employed, but it can degrade performance, particularly when the input SF is lower than the trained SF. This paper investigates the causes of this degradation through...
Qualitative research often contains personal, contextual, and organizational details that pose privacy risks if not handled appropriately. Manual anonymization is time-consuming, inconsistent, and frequently omits critical identifiers. Existing automated tools tend to rely on pattern matching or fixed rules, which fail to capture...
In this paper, we generalize the Dirac-dual-Dirac method to Hecke pairs with equivariant coarse embeddings and establish the K-theoretic isomorphisms between the maximal and reduced equivariant Roe algebras. We also extend these results to prove the Baum--Connes conjecture in this context.
This work advances autonomous robot exploration by integrating agent-level semantic reasoning with fast local control. We introduce FARE, a hierarchical autonomous exploration framework that integrates a large language model (LLM) for global reasoning with a reinforcement learning (RL) policy for local decision making. FARE follows a...
We introduce a nearly parameter-free algorithm for minimizing piecewise smooth (PWS) convex functions under the quadratic-growth (QG) condition, where the locations and structure of the smooth regions are entirely unknown. Our algorithm, APEX (Accelerated Prox-Level method for Exploring Piecewise Smoothness), is an accelerated...
Commercial insurance underwriting is a labor-intensive process that requires manual review of extensive documentation to assess risk and determine policy pricing. While AI offers substantial efficiency improvements, existing solutions lack comprehensive reasoning and internal mechanisms to ensure reliability in regulated, high-stakes...
Natural walking enhances immersion in virtual environments (VEs), but physical space limitations and obstacles hinder exploration, especially in large virtual scenes. Redirected Walking (RDW) techniques mitigate this by subtly manipulating the virtual camera to guide users away from physical collisions within pre-defined VEs. However,...
Supervised deep learning models often achieve excellent performance within their training distribution but struggle to generalize beyond it. In cancer histopathology, for example, a convolutional neural network (CNN) may classify cancer severity accurately for cancer types represented in its training data, yet fail on related but...
Object detection in video and image surveillance is a well-established yet rapidly evolving task, strongly influenced by recent deep learning advancements. This review summarises modern techniques by examining architectural innovations, generative model integration, and the use of temporal information to enhance robustness and...
We identify an oscillatory solution that exists as a long-lived, bubble-like closed domain wall in the two-Higgs-doublet model (2HDM) under a $\mathbb{Z}_2$ symmetry constraint, and these structures emerge naturally during the late stages of domain wall decay. \\ \\ The longevity of these structures is attributed to a potential...
Double source plane strong lensing (DSPL) systems offer a robust, independent probe of cosmological parameters. The Chinese Space Station Telescope (CSST) is expected to discover hundreds of DSPLs, yet the survey modes and system configurations that best enable cosmological inference remain uncertain. To investigate the impact of...
Given a monocular video, the goal of video re-rendering is to generate views of the scene from a novel camera trajectory. Existing methods face two distinct challenges. Geometrically unconditioned models lack spatial awareness, leading to drift and deformation under viewpoint changes. On the other hand, geometrically-conditioned...
The ongoing decarbonisation of power systems is driving an increasing reliance on distributed energy resources, which introduces complex and nonlinear interactions that are difficult to capture in conventional optimisation models. As a result, machine learning based surrogate modelling has emerged as a promising approach, but...
Hyperparameter tuning is a critical yet computationally expensive step in training neural networks, particularly when the search space is high dimensional and nonconvex. Metaheuristic optimization algorithms are often used for this purpose due to their derivative free nature and robustness against local optima. In this work, we...
Autoregressive (AR) visual generators model images as sequences of discrete tokens and are trained with a next-token likelihood objective. This strict causal supervision optimizes each step based only on the immediate next token, which can weaken global coherence and slow convergence. We investigate whether foresight, training signals...
Inverse design is a commonly used methodology for creating devices that manipulate electromagnetic (EM) waves by algorithmically modifying device parameters to achieve a desired functionality. Utilizing plasma, a dynamically tunable medium, allows the optimization of the design process to be conducted directly on the experimental...
We show that the macroscopic version of Gromov's Urysohn width conjecture for scalar curvature is false in dimensions four and above. This is based on (1) a novel estimate on the codimension two Urysohn width of circle bundles over manifolds with large hypersphericity radius, and (2) a notion of ruling for Riemannian manifolds that...
In this paper, we study Iwasawa theory for Tate motives over totally real fields. More precisely, we construct a zeta element that interpolates the values of $L$-functions at positive integers over totally real fields under a certain unramified condition at $p$. As an application of this, we construct a canonical element in the...
The rapid advancement of Large Language Model (LLM)-based Multi-Agent Systems (MAS) has introduced significant security vulnerabilities, where malicious influence can propagate virally through inter-agent communication. Conventional safeguards often rely on a binary paradigm that strictly distinguishes between benign and attack...
Determining how galaxies accumulate stellar mass is paramount to understanding the Universe. Two primary mechanisms drive this process: star-formation (SF) & mergers. Our understanding of star formation, and to some degree the processes that influence the baryon cycle (environment, gas supply, feedback, etc), are either relatively...
The rapid growth of artificial intelligence (AI)-driven data centers is reshaping electricity demand patterns. This is achieved by introducing fast, multi-gigawatt load ramps that challenge the stability and resilience of modern power systems. Traditional resilience frameworks focus mainly on physical outages and largely overlook...
We investigate proper infall times in the Schwarzschild and Kerr spacetimes from a covariant perspective, focusing on the role of black--hole rotation in the focusing properties of timelike geodesic congruences.To perform a geometrically consistent comparison between rotating and non--rotating black holes, we analyse infall...
Reliable forecasting of prosumer flexibility is critical for demand response aggregators participating in frequency controlled ancillary services market, where strict reliability requirements such as the P90 standard are enforced. Limited historical data, dependence on exogeneous factors, and heterogenous prosumer behaviour introduce...
Graph-based retrieval-augmented generation (GraphRAG) systems construct knowledge graphs over document collections to support multi-hop reasoning. While prior work shows that GraphRAG responses may leak retrieved subgraphs, the feasibility of query-efficient reconstruction of the hidden graph structure remains unexplored under...