Research

Papers

Research papers from arXiv and related sources

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

Trust via Reputation of Conviction

The question of \emph{knowledge}, \emph{truth} and \emph{trust} is explored via a mathematical formulation of claims and sources. We define truth as the reproducibly perceived subset of knowledge, ...

Aravind R. Iyengar

2603.08575 2026-03-09
AI LLM

OSS-CRS: Liberating AIxCC Cyber Reasoning Systems for Real-World Open-Source Security

DARPA's AI Cyber Challenge (AIxCC) showed that cyber reasoning systems (CRSs) can go beyond vulnerability discovery to autonomously confirm and patch bugs: seven teams built such systems and open-s...

Andrew Chin, Dongkwan Kim, Yu-Fu Fu, Fabian Fleischer, Youngjoon Kim, HyungSeok Han, Cen Zhang, B...

2603.08566 2026-03-09
AI LLM

RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback

Large language model (LLM)-based agents trained with reinforcement learning (RL) have shown strong potential on complex interactive tasks. However, standard RL paradigms favor static problem-solvin...

Xiaoying Zhang, Zichen Liu, Yipeng Zhang, Xia Hu, Wenqi Shao

2603.08561 2026-03-09
TESTING

Multi-epoch afterglow rebrightenings in GRB 250129A: Evidence for successive shock interactions

Most long gamma-ray bursts (GRBs) exhibit afterglows broadly consistent with external forward-shock emission, typically described by smooth broken power-law decays in the multiband light curve. How...

D. Akl, S. Antier, H. Koehn, P. T. H. Pang, J. J. Geng, R. Gill, E. Abdikamalov, C. Adami, V. Aiv...

2603.08555 2026-03-09
TESTING

Emergence of an Advective Boundary Layer in Monsoon Cross-Equatorial Flow: Scaling, Dynamics, and Idealized Models

The conventional Ekman model of the tropical boundary layer neglects nonlinear momentum advection and breaks down near the equator, where Coriolis effects are weak. During South Asian monsoon onset...

Rajat Masiwal, Ashwin K Seshadri, Vishal Dixit

2603.08550 2026-03-09
TESTING

Minimax estimation for Varying Coefficient Model via Laguerre Series

We delve into the estimation of the functional coefficients and inference for varying coefficient model. Applying Laguerre series, we develop an estimator for the vector of functional coefficients ...

Rida Benhaddou, Khalid Chokri, Jackson Pinschenat

2603.08538 2026-03-09
TESTING

TUMSphere: Turning a University Curriculum into Playable VR Challenges

Traditional university orientation formats struggle to convey the intellectual substance of STEM curricula, particularly in disciplines where core competencies, such as algorithmic thinking and for...

Santiago Berrezueta-Guzman, Nadia Damianova, Andrei Koshelev, Ivan Parmacli, Stefan Wagner

2603.08525 2026-03-09
AI LLM

SCAFFOLD-CEGIS: Preventing Latent Security Degradation in LLM-Driven Iterative Code Refinement

The application of large language models to code generation has evolved from one-shot generation to iterative refinement, yet the evolution of security throughout iteration remains insufficiently u...

Yi Chen, Yun Bian, Haiquan Wang, Shihao Li, Zhe Cui

2603.08520 2026-03-09
TESTING

Ashes of FIRE: Modeling Dust Grain Size Evolution in the Local Group with FIRE

We introduce a new, discretized grain size evolution model, incorporated into the GIZMO code and coupled with FIRE-3 stellar feedback and ISM physics, to investigate variations in dust abundance, c...

Caleb R. Choban, Samir Salim, Dušan Kereš, Julia Roman-Duval, Karin M. Sandstrom

2603.08504 2026-03-09
AI LLM

Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA

Large language models (LLMs) can answer religious knowledge queries fluently, yet they often hallucinate and misattribute sources, which is especially consequential in Islamic settings where users ...

Ummar Abbas, Mourad Ouzzani, Mohamed Y. Eltabakh, Omar Sinan, Gagan Bhatia, Hamdy Mubarak, Majd H...

2603.08501 2026-03-09
TESTING

All Vehicles Can Lie: Efficient Adversarial Defense in Fully Untrusted-Vehicle Collaborative Perception via Pseudo-Random Bayesian Inference

Collaborative perception (CP) enables multiple vehicles to augment their individual perception capacities through the exchange of feature-level sensory data. However, this fusion mechanism is inher...

Yi Yu, Libing Wu, Zhuangzhuang Zhang, Jing Qiu, Lijuan Huo, Jiaqi Feng

2603.08498 2026-03-09
AI LLM

Towards Modeling Cybersecurity Behavior of Humans in Organizations

We undertake a comprehensive and structured synthesis of the drivers of human behavior in cybersecurity, focusing specifically on people within organizations (i.e., especially employees in companie...

Klaas Ole Kürtz

2603.08484 2026-03-09
AI LLM

Behavioral Generative Agents for Power Dispatch and Auction

This paper presents positive initial evidence that generative agents can relax the rigidity of traditional mathematical models for human decision-making in power dispatch and auction settings. We d...

Shaoze Li, Justin S. Kim, Cong Chen

2603.08477 2026-03-09
AI LLM

R2F: Repurposing Ray Frontiers for LLM-free Object Navigation

Zero-shot open-vocabulary object navigation has progressed rapidly with the emergence of large Vision-Language Models (VLMs) and Large Language Models (LLMs), now widely used as high-level decision...

Francesco Argenziano, John Mark Alexis Marcelo, Michele Brienza, Abdel Hakim Drid, Emanuele Musum...

2603.08475 2026-03-09
TESTING

Extreme mass loss during common envelope evolution: the origin of the double low-mass white dwarf system J2102--4145

Eclipsing close double white dwarf (WD) systems provide a unique opportunity to directly constrain hydrogen-envelope retention and test common-envelope (CE) evolution in low-mass stars, since they ...

Leandro G. Althaus, Alejandro H. Corsico, Monica Zorotovic, Maja Vuckovic, Alberto Rebassa-Manser...

2603.08470 2026-03-09
AI LLM

Amplitude Analysis of Singly Cabibbo-Suppressed Decay $Λ^{+}_{c}\to p K^{+} K^{-}$

Using a sample of $e^{+}e^{-}$ annihilation data corresponding to an integrated luminosity of 4.4 $\rm{fb}^{-1}$ collected with the BESIII detector at the BEPCII collider and produced at center-of-...

BESIII Collaboration, M. Ablikim, M. N. Achasov, P. Adlarson, X. C. Ai, R. Aliberti, A. Amoroso,...

2603.08469 2026-03-09
AI LLM

Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck

Chain-of-Thought (CoT) prompting improves LLM accuracy on complex tasks but often increases token usage and inference cost. Existing "Budget Forcing" methods reducing cost via fine-tuning with heur...

Fabio Valerio Massoli, Andrey Kuzmin, Arash Behboodi

2603.08462 2026-03-09
AI LLM

Data-Driven Priors for Uncertainty-Aware Deterioration Risk Prediction with Multimodal Data

Safe predictions are a crucial requirement for integrating predictive models into clinical decision support systems. One approach for ensuring trustworthiness is to enable models' ability to expres...

L. Julián Lechuga López, Tim G. J. Rudner, Farah E. Shamout

2603.08459 2026-03-09
AI LLM

LycheeCluster: Efficient Long-Context Inference with Structure-Aware Chunking and Hierarchical KV Indexing

The quadratic complexity of the attention mechanism and the substantial memory footprint of the Key-Value (KV) cache present severe computational and memory challenges for Large Language Models (LL...

Dongfang Li, Zixuan Liu, Gang Lin, Baotian Hu, Min Zhang

2603.08453 2026-03-09
AI LLM

A Dataset for Probing Translationese Preferences in English-to-Swedish Translation

Translations often carry traces of the source language, a phenomenon known as translationese. We introduce the first freely available English-to-Swedish dataset contrasting translationese sentences...

Jenny Kunz, Anja Jarochenko, Marcel Bollmann

2603.08450 2026-03-09