8 papers
SkillMutator: Benchmarking and Defending Language-and-Code Cross-modal Attacks on LLM Agent Skills
Youngduk Kim, Minkyoo Song, Seungwon Shin
Large language model (LLM) agents increasingly extend their capabilities at runtime by loading Agent Skills, which pair natural-language specifications (SKILL.md) with executable s…
Can LLMs Solve Science or Just Write Code? Evaluating Quantum Solver Generation
Luciano Baresi, Domenico Bianculli, Maryse Ernzer +3
Large Language Models (LLMs) show strong capabilities in code generation, motivating their use in automated quantum solver development. However, in quantum computing, successful ex…
Randomized and Diverse Input State Generation for Quantum Program Testing
Maryse Ernzer, Seung Yeob Shin, Fabrizio Pastore +1
With the accelerating development of quantum technologies and their growing computational potential, quantum systems are being adapted for simulations and other critical tasks acro…
Beyond Rules: LLM-Powered Linting for Quantum Programs
Pietro Cassieri, Giuseppe Scanniello, Seung Yeob Shin +2
As quantum computing transitions from theoretical experimentation to its practical application, the reliability of quantum software has become a critical bottleneck. Traditional st…
Test Schedule Generation for Acceptance Testing of Mission-Critical Satellite Systems
Raphaël Ollando, Seung Yeob Shin, Mario Minardi +1
Mission-critical system, such as satellite systems, healthcare systems, and nuclear power plant control systems, undergo rigorous testing to ensure they meet specific operational r…
Testing CPS with Design Assumptions-Based Metamorphic Relations and Genetic Programming
Claudio Mandrioli, Seung Yeob Shin, Domenico Bianculli +1
Cyber-Physical Systems (CPSs) software is used to enforce desired behaviours on physical systems. To test the interaction between the CPS software and the system's physics, enginee…