arXiv preprints from January 1, 2026 through September 13, 2026 — 02:19:46 EST
The emergence of Agentic AI systems has outpaced the architectural thinking required to operate them effectively. These agents differ fundamentally from traditional software: their behavior is not fixed at deployment but continuously shaped by experience, feedback, and context. Applying operational principles inherited from DevOps or...
Large language models (LLMs) are increasingly grounded in sensor data to perceive and reason about human physiology and the physical world. However, accurately interpreting heterogeneous multimodal sensor data remains a fundamental challenge. We show that a single monolithic LLM often fails to reason coherently across modalities,...
Food cutting is a highly practical yet underexplored application at the intersection of vision and robotic manipulation. The task remains challenging because interactions between the knife and deformable materials are highly nonlinear and often entail large deformations, frequent contact, and topological change, which in turn hinder...
For Indigenous Peoples of the Apya Yala (or Abya Yala), particularly in the Kara and Kichwa citizens of the Pan-Andean-Amazonian biocultural region, data is not merely a knowledge or information resource, it is the extension of Khipu Panaka (Indigenous data authority), treading the data lifecycle, genealogical and relational memory...
Open-ended tasks, such as coding problems that are common in computer science education, provide detailed insights into student knowledge. However, training large language models (LLMs) to simulate and predict possible student errors in their responses to these problems can be challenging: they often suffer from mode collapse and fail...
Building NLP systems for subjective tasks requires one to ensure their alignment to contrasting human values. We propose the MultiCalibrated Subjective Task Learner framework (MC-STL), which clusters annotations into identifiable human value clusters by three approaches (similarity of annotator rationales, expert-value taxonomies or...
Learned index structures aim to accelerate queries by training machine learning models to approximate the rank function associated with a database attribute. While effective in practice, their theoretical limitations are not fully understood. We present a general framework for proving lower bounds on query time for learned indexes,...
This study presents a Secure Multi-Tenant Architecture (SMTA) combined with a novel concept Burn-After-Use (BAU) mechanism for enterprise LLM environments to effectively prevent data leakage. As institutions increasingly adopt LLMs across departments, the risks of data leakage have become a critical security and compliance concern....
Artificial intelligence research faces a critical ethical paradox: determining whether AI systems are conscious requires experiments that may harm entities whose moral status remains uncertain. Recent work proposes avoiding consciousness-uncertain AI systems entirely, yet this faces practical limitations-we cannot guarantee such...
Named Entity Linking (NEL) is a core component of biomedical Information Extraction (IE) pipelines, yet assessing its quality at scale is challenging due to the high cost of expert annotations and the large size of corpora. In this paper, we present a sampling-based framework to estimate the NEL accuracy of large-scale IE corpora...
Upper aerodigestive tract (UADT) treatments frequently employ transoral laser microsurgery (TLM) for procedures such as the removal of tumors or polyps. In TLM, a laser beam is used to cut target tissue, while forceps are employed to grasp, manipulate, and stabilize tissue within the UADT. Although TLM systems may rely on different...
The integration of Large Language Models (LLMs) into interactive systems opens new opportunities for adaptive user experiences, yet it also raises challenges regarding accessibility, explainability, and normative compliance. This paper presents an implemented model-driven architecture for generating personalised, multimodal, and...
Current Large Language Models (LLMs) have advanced automated unit test generation but face a critical limitation: they often neglect to construct the necessary test fixtures, which are the environmental setups required for a test to run. To bridge this gap, this paper proposes Fixturize, a diagnostic framework that proactively...
Although the Asset Administration Shell (AAS) standard provides a structured and machine-readable representation of industrial assets, their semantic comparability remains a major challenge, particularly when different vocabularies and modeling practices are used. Engineering would benefit from retrieving existing AAS models that are...
The reliance of Large Language Models and Internet of Things systems on massive, globally distributed data flows creates systemic security and privacy challenges. When data traverses borders, it becomes subject to conflicting legal regimes, such as the EU's General Data Protection Regulation and China's Personal Information Protection...
The rapid evolution of artificial intelligence (AI) systems, tools, and technologies has opened up novel, unprecedented opportunities for businesses to innovate, differentiate, and compete. However, growing concerns have emerged about the use of AI in businesses, particularly AI washing, in which firms exaggerate, misrepresent, or...
This paper presents the study of the symplectic hulls over a non-unital ring $ E= \langle κ,τ\mid 2 κ=2 τ=0,~ κ^2=κ,~ τ^2=τ,~ κτ=κ,~ τκ=τ\rangle$. We first identify the residue and torsion codes of the left, right, and two-sided symplectic hulls, and characterize the generator matrix of the two-sided symplectic hull of a free...
Sanskrit Subhasitas encapsulate centuries of cultural and philosophical wisdom, yet remain underutilized in the digital age due to linguistic and contextual barriers. In this work, we present Pragya, a retrieval-augmented generation (RAG) framework for semantic recommendation of Subhasitas. We curate a dataset of 200 verses annotated...
While machine learning shows promise for maternal health risk prediction, clinical adoption in resource-constrained settings faces a critical barrier: lack of explainability and trust. This study presents a hybrid explainable AI (XAI) framework combining ante-hoc fuzzy logic with post-hoc SHAP explanations, validated through...
We demonstrate CEDAR, an application for automating data science (DS) tasks with an agentic setup. Solving DS problems with LLMs is an underexplored area that has immense market value. The challenges are manifold: task complexities, data sizes, computational limitations, and context restrictions. We show that these can be alleviated...
Text-guided image generation has advanced rapidly with large-scale diffusion models, yet achieving precise stylization with visual exemplars remains difficult. Existing approaches often depend on task-specific retraining or expensive inversion procedures, which can compromise content integrity, reduce style fidelity, and lead to an...
In this paper, we introduce ObjectZero, a novel reinforcement learning (RL) algorithm that leverages the power of object-level representations to model dynamic environments more effectively. Unlike traditional approaches that process the world as a single undifferentiated input, our method employs Graph Neural Networks (GNNs) to...
Multi-hop question answering over hybrid table-text data requires retrieving and reasoning across multiple evidence pieces from large corpora, but standard Retrieval-Augmented Generation (RAG) pipelines process documents as flat ranked lists, causing retrieval noise to obscure reasoning chains. We introduce N2N-GQA. To our knowledge,...
Inertial localization is particularly valuable in GPS-denied environments such as indoors. However, localization using only Inertial Measurement Units (IMUs) suffers from drift caused by motion-process noise and sensor biases. This paper introduces Uncertainty-aware Map-constrained Inertial Localization (UMLoc), an end-to-end...
Short-video platforms have become major channels for misinformation, where deceptive claims frequently leverage visual experiments and social cues. While Multimodal Large Language Models (MLLMs) have demonstrated impressive reasoning capabilities, their robustness against misinformation entangled with cognitive biases remains...