Research

Papers

Research papers from arXiv and related sources

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

Neuro-Symbolic Artificial Intelligence: A Task-Directed Survey in the Black-Box Models Era

The integration of symbolic computing with neural networks has intrigued researchers since the first theorizations of Artificial intelligence (AI). The ability of Neuro-Symbolic (NeSy) methods to i...

Giovanni Pio Delvecchio, Lorenzo Molfetta, Gianluca Moro

2603.03177 2026-03-03
AI LLM

Saarthi for AGI: Towards Domain-Specific General Intelligence for Formal Verification

Saarthi is an agentic AI framework that uses multi-agent collaboration to perform end-to-end formal verification. Even though the framework provides a complete flow from specification to coverage c...

Aman Kumar, Deepak Narayan Gadde, Luu Danh Minh, Vaisakh Naduvodi Viswambharan, Keerthan Kopparam...

2603.03175 2026-03-03
TESTING

Data Unfolding: From Problem Formulation to Result Assessment

Experimental data in particle and nuclear physics, particle astrophysics, and radiation protection dosimetry are collected using experimental facilities that consist of a complex system of sensors,...

Nikolay D. Gagunashvili

2603.03168 2026-03-03
TESTING

Testing gravitational wave polarizations with LISA

In this paper we quantify the ability of the Laser Interferometer Space Antenna (LISA) to test the presence of non-tensorial polarizations as well as modifications to the tensor ones in gravitation...

Shingo Akama, Maxence Corman, Paola C. M. Delgado, Alice Garoffolo, Macarena Lagos, Alberto Mangi...

2603.03165 2026-03-03
AI LLM

Conditioned Activation Transport for T2I Safety Steering

Despite their impressive capabilities, current Text-to-Image (T2I) models remain prone to generating unsafe and toxic content. While activation steering offers a promising inference-time interventi...

Maciej Chrabąszcz, Aleksander Szymczyk, Jan Dubiński, Tomasz Trzciński, Franziska Boenisch, Adam ...

2603.03163 2026-03-03
AI LLM

An Investigation Into Various Approaches For Bengali Long-Form Speech Transcription and Bengali Speaker Diarization

Bengali remains a low-resource language in speech technology, especially for complex tasks like long-form transcription and speaker diarization. This paper presents a multistage approach developed ...

Epshita Jahan, Khandoker Md Tanjinul Islam, Pritom Biswas, Tafsir Al Nafin

2603.03158 2026-03-03
TESTING

Weak-Strong Uniqueness for a Rigid Body Immersed in an Inviscid Compressible Fluid

We consider the coupled motion of a free rigid body immersed in an inviscid compressible isentropic fluid. By means of a vanishing viscosity limit, we obtain the local-in-time existence of a dissip...

Qianfeng Li, Emil Wiedemann

2603.03151 2026-03-03
AI LLM

From Language to Action: Can LLM-Based Agents Be Used for Embodied Robot Cognition?

In order to flexibly act in an everyday environment, a robotic agent needs a variety of cognitive capabilities that enable it to reason about plans and perform execution recovery. Large language mo...

Shinas Shaji, Fabian Huppertz, Alex Mitrevski, Sebastian Houben

2603.03148 2026-03-03
AI LLM

Agentic AI-based Coverage Closure for Formal Verification

Coverage closure is a critical requirement in Integrated Chip (IC) development process and key metric for verification sign-off. However, traditional exhaustive approaches often fail to achieve ful...

Sivaram Pothireddypalli, Ashish Raman, Deepak Narayan Gadde, Aman Kumar

2603.03147 2026-03-03
AI LLM

Channel-Adaptive Edge AI: Maximizing Inference Throughput by Adapting Computational Complexity to Channel States

\emph{Integrated communication and computation} (IC$^2$) has emerged as a new paradigm for enabling efficient edge inference in sixth-generation (6G) networks. However, the design of IC$^2$ technol...

Jierui Zhang, Jianhao Huang, Kaibin Huang

2603.03146 2026-03-03
AI LLM

The Household Impact of Generative AI: Evidence from Internet Browsing Behavior

This paper studies the impact of generative AI on U.S. households' task allocation at home, using detailed Internet browsing data from a large sample of home devices between 2021 and 2024. Leveragi...

Michael Blank, Gregor Schubert, Miao Ben Zhang

2603.03144 2026-03-03
AI LLM

APRES: An Agentic Paper Revision and Evaluation System

Scientific discoveries must be communicated clearly to realize their full potential. Without effective communication, even the most groundbreaking findings risk being overlooked or misunderstood. T...

Bingchen Zhao, Jenny Zhang, Chenxi Whitehouse, Minqi Jiang, Michael Shvartsman, Abhishek Charnali...

2603.03142 2026-03-03
AI LLM

How to Model AI Agents as Personas?: Applying the Persona Ecosystem Playground to 41,300 Posts on Moltbook for Behavioral Insights

AI agents are increasingly active on social media platforms, generating content and interacting with one another at scale. Yet the behavioral diversity of these agents remains poorly understood, an...

Danial Amin, Joni Salminen, Bernard J. Jansen

2603.03140 2026-03-03
AI LLM

UniSkill: A Dataset for Matching University Curricula to Professional Competencies

Skill extraction and recommendation systems have been studied from recruiter, applicant, and education perspectives. While AI applications in job advertisements have received broad attention, defic...

Nurlan Musazade, Joszef Mezei, Mike Zhang

2603.03134 2026-03-03
TESTING

Joint Training Across Multiple Activation Sparsity Regimes

Generalization in deep neural networks remains only partially understood. Inspired by the stronger generalization tendency of biological systems, we explore the hypothesis that robust internal repr...

Haotian Wang

2603.03131 2026-03-03
TESTING

Estimating the dynamical masses of dwarf galaxies in the presence of binary-star contamination

Ultra-faint dwarf galaxies (UFDs) show extreme dynamical mass-to-light ratios of approximately 100-5000 in solar units within the half-light radius, making them critical tests for cosmological mode...

José María Arroyo-Polonio, Giuseppina Battaglia, Guillaume F. Thomas

2603.03129 2026-03-03
TESTING

Behavior Change as a Signal for Identifying Social Media Manipulation

Social media accounts engaging in online manipulation can change their behaviors for re-purposing or to evade detection. Existing detection systems are built on features that do not exploit such be...

Isuru Ariyarathne, Gangani Ariyarathne, Alessandro Flammini, Filippo Menczer, Alexander C. Nwala

2603.03128 2026-03-03
AI LLM

The Science Data Lake: A Unified Open Infrastructure Integrating 293 Million Papers Across Eight Scholarly Sources with Embedding-Based Ontology Alignment

Scholarly data are largely fragmented across siloed databases with divergent metadata and missing linkages among them. We present the Science Data Lake, a locally-deployable infrastructure built on...

Jonas Wilinski

2603.03126 2026-03-03
AI LLM

RippleGUItester: Change-Aware Exploratory Testing

Software systems evolve continuously through frequent code changes, yet such changes often introduce unintended bugs despite extensive testing and code review. Existing testing approaches are large...

Yanqi Su, Michael Pradel, Chunyang Chen

2603.03121 2026-03-03
AI LLM

AI Space Physics: Constitutive boundary semantics for open AI institutions

Agentic AI deployments increasingly behave as persistent institutions rather than one-shot inference endpoints: they accumulate state, invoke external tools, coordinate multiple runtimes, and modif...

Oleg Romanchuk, Roman Bondar

2603.03119 2026-03-03