Research

Papers

Research papers from arXiv and related sources

Total: 4694 AI/LLM: 2583 Testing: 2111
AI LLM

From Digital Twins to World Models:Opportunities, Challenges, and Applications for Mobile Edge General Intelligence

The rapid evolution toward 6G and beyond communication systems is accelerating the convergence of digital twins and world models at the network edge. Traditional digital twins provide high-fidelity...

Jie Zheng, Dusit Niyato, Changyuan Zhao, Jiawen Kang, Jiacheng Wang

2603.17420 2026-03-18
AI LLM

Caging the Agents: A Zero Trust Security Architecture for Autonomous AI in Healthcare

Autonomous AI agents powered by large language models are being deployed in production with capabilities including shell execution, file system access, database queries, and multi-party communicati...

Saikat Maiti

2603.17419 2026-03-18
AI LLM

PowerDAG: Reliable Agentic AI System for Automating Distribution Grid Analysis

This paper introduces PowerDAG, an agentic AI system for automating complex distribution-grid analysis. We address the reliability challenges of state-of-the-art agentic systems in automating compl...

Emmanuel O. Badmus, Amritanshu Pandey

2603.17418 2026-03-18
AI LLM

Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)

Current Large Language Models (LLMs) are gradually exploited in practically valuable agentic workflows such as Deep Research, E-commerce recommendation, and job recruitment. In these applications, ...

Zichen Tang, Zirui Zhang, Qian Wang, Zhenheng Tang, Bo Li, Xiaowen Chu

2603.17417 2026-03-18
TESTING

Towards Motion-aware Referring Image Segmentation

Referring Image Segmentation (RIS) requires identifying objects from images based on textual descriptions. We observe that existing methods significantly underperform on motion-related queries comp...

Chaeyun Kim, Seunghoon Yi, Yejin Kim, Yohan Jo, Joonseok Lee

2603.17413 2026-03-18
AI LLM

Bootstrapping Coding Agents: The Specification Is the Program

A coding agent can bootstrap itself. Starting from a 926-word specification and a first implementation produced by an existing agent (Claude Code), a newly generated agent re-implements the same sp...

Martin Monperrus

2603.17399 2026-03-18
AI LLM

Agentic Cognitive Profiling: Realigning Automated Alzheimer's Disease Detection with Clinical Construct Validity

Automated Alzheimer's Disease (AD) screening has predominantly followed the inductive paradigm of pattern recognition, which directly maps the input signal to the outcome label. This paradigm sacri...

Jiawen Kang, Kun Li, Dongrui Han, Jinchao Li, Junan Li, Lingwei Meng, Xixin Wu, Helen Meng

2603.17392 2026-03-18
TESTING

A Cycle-Based Solvability Condition for Real Power Flow Equations

The solvability condition of the power flow equation is important in operational planning and control as it guarantees the existence and uniqueness of a solution for a given set of power injections...

Puskar Neupane, Bai Cui

2603.17376 2026-03-18
TESTING

OmniVLN: Omnidirectional 3D Perception and Token-Efficient LLM Reasoning for Visual-Language Navigation across Air and Ground Platforms

Language-guided embodied navigation requires an agent to interpret object-referential instructions, search across multiple rooms, localize the referenced target, and execute reliable motion toward ...

Zhongyuang Liu, Min He, Shaonan Yu, Xinhang Xu, Muqing Cao, Jianping Li, Jianfei Yang, Lihua Xie

2603.17351 2026-03-18
TESTING

Lepton flavor violating $τ^- \to \ell_i^- \ell_i^- \ell_j^+$ ($\ell_i\neq \ell_j$) decays induced by $S_1$ and $R_2$ scalar leptoquarks

Charged lepton flavor violation provides a clear experimental signature in the search for physics beyond the Standard Model. In this work, we study the flavor-violating three-body tau decays $τ^- \...

G. Hernández-Tomé, J. P. Hoyos-Daza, O. G. Miranda, R. Sánchez-Vélez

2603.17350 2026-03-18
TESTING

Design and First Results of COFFEE3: A 55nm HVCMOS Pixel Sensor Prototype for High-Energy Physics Applications

Motivated by the stringent requirements of the Upstream Pixel (UP) tracker in the LHCb Upgrade II and the Inner Tracking detector (ITK) of the Circular Electron Positron Collider, the COFFEE series...

Xiaomin Wei, Zijun Xu, Weiguo Lu, Yang Zhou, Zhan Shi, Leyi Li, Xiaoxu Zhang, Pengxu Li, Jianpeng...

2603.17346 2026-03-18
TESTING

Bar-Informed Kinematic-Distance Mapping of Molecular Gas in the Inner Milky Way

We present a bar-informed kinematic-distance (BIKD) method to reconstruct face-on molecular-gas maps of the inner Milky Way from PPV data, relaxing the standard assumption of axisymmetric circular ...

Junichi Baba

2603.17341 2026-03-18
TESTING

citecheck: An MCP Server for Automated Bibliographic Verification and Repair in Scholarly Manuscripts

Reference lists in scholarly manuscripts frequently contain errors, including incorrect identifiers, incomplete metadata, misattributed authors, and mismatches between preprint and published versio...

Junhyeok Lee

2603.17339 2026-03-18
TESTING

Federated Computing as Code (FCaC): Sovereignty-aware Systems by Design

Federated computing (FC) enables collaborative computation such as machine learning, analytics, or data processing across distributed organizations keeping raw data local. Built on four architectur...

Enzo Fenoglio, Philip Treleaven

2603.17331 2026-03-18
TESTING

GUIDE: GenAI Units In Digital Design Education

GenAI Units In Digital Design Education (GUIDE) is an open courseware repository with runnable Google Colab labs and other materials. We describe the repository's architecture and educational appro...

Weihua Xiao, Jason Blocklove, Matthew DeLorenzo, Johann Knechtel, Ozgur Sinanoglu, Kanad Basu, Je...

2603.17296 2026-03-18
TESTING

Revisiting Vulnerability Patch Identification on Data in the Wild

Attacks can exploit zero-day or one-day vulnerabilities that are not publicly disclosed. To detect these vulnerabilities, security researchers monitor development activities in open-source reposito...

Ivana Clairine Irsan, Ratnadira Widyasari, Ting Zhang, Huihui Huang, Ferdian Thung, Yikun Li, Lwi...

2603.17266 2026-03-18
TESTING

Physics of Collectivity and EOS from the RHIC Beam Energy Scan Program

In this article we will review recent measurements of directed flow $v_1$ and elliptic flow $v_2$ in Au+Au collisions from the STAR Beam Energy Scan (BES) program. We systematically analyze the $v_...

Xionghong He, Shusu Shi, Nu Xu

2603.17260 2026-03-18
TESTING

AppFlow: Memory Scheduling for Cold Launch of Large Apps on Mobile and Vehicle Systems

GB-scale large apps like on-device LLMs and rich media editors are becoming the next-generation trend, but their heavy memory and I/O demands, especially during multitasking, cause devices to recla...

Xiaochen Li, Sicong Liu, Bin Guo, Yu Ouyang, Fengmin Wu, Yuan Xu, Zhiwen Yu

2603.17259 2026-03-18
TESTING

Graph-Native Cognitive Memory for AI Agents: Formal Belief Revision Semantics for Versioned Memory Architectures

While individual components for AI agent memory exist in prior systems, their architectural synthesis and formal grounding remain underexplored. We present Kumiho, a graph-native cognitive memory a...

Young Bin Park

2603.17244 2026-03-18
TESTING

LAAF: Logic-layer Automated Attack Framework A Systematic Red-Teaming Methodology for LPCI Vulnerabilities in Agentic Large Language Model Systems

Agentic LLM systems equipped with persistent memory, RAG pipelines, and external tool connectors face a class of attacks - Logic-layer Prompt Control Injection (LPCI) - for which no automated red-t...

Hammad Atta, Ken Huang, Kyriakos Rock Lambros, Yasir Mehmood, Zeeshan Baig, Mohamed Abdur Rahman,...

2603.17239 2026-03-18