34 citations · 120 across the 14 of their papers we have counts for
14 papers · 1 filter
AgentSpy: Making AI Agent Behavior Observable
Christoph Bühler, Matteo Biagiola, Luca Di Grazia +1
AI agents built on large language models (LLMs) run shell commands, read and write files, and reach the network, typically with their user's privileges. However, what an agent does…
The Alignment Problem in Constrained Code Generation
Matteo Biagiola, Jahrim Gabriele Cesario, Luca Di Grazia +2
Large Language Models (LLMs) have demonstrated strong capabilities in code generation, but their outputs frequently contain syntax or type errors that result in compilation failure…
Towards Automated Page Object Generation for Web Testing using Large Language Models
Betül Karagöz, Filippo Ricca, Matteo Biagiola +1
Page Objects (POs) are a widely adopted design pattern for improving the maintainability and scalability of automated end-to-end web tests. However, creating and maintaining POs is…
Simulator Ensembles for Trustworthy Autonomous Driving Systems Testing
Lev Sorokin, Matteo Biagiola, Andrea Stocco
Scenario-based testing with driving simulators is extensively used to identify failing conditions of automated driving assistance systems (ADAS). However, existing studies have sho…
XMutant: XAI-based Fuzzing for Deep Learning Systems
Xingcheng Chen, Matteo Biagiola, Vincenzo Riccio +2
Semantic-based test generators are widely used to produce failure-inducing inputs for Deep Learning (DL) systems. They typically generate challenging test inputs by applying random…
Improving the Readability of Automatically Generated Tests using Large Language Models
Matteo Biagiola, Gianluca Ghislotti, Paolo Tonella
Search-based test generators are effective at producing unit tests with high coverage. However, such automatically generated tests have no meaningful test and variable names, makin…
Adaptive Random Testing with Q-grams: The Illusion Comes True
Matteo Biagiola, Robert Feldt, Paolo Tonella
Adaptive Random Testing (ART) has faced criticism, particularly for its computational inefficiency, as highlighted by Arcuri and Briand. Their analysis clarified how ART requires a…
muPRL: A Mutation Testing Pipeline for Deep Reinforcement Learning based on Real Faults
Deepak-George Thomas, Matteo Biagiola, Nargiz Humbatova +4
Reinforcement Learning (RL) is increasingly adopted to train agents that can deal with complex sequential tasks, such as driving an autonomous vehicle or controlling a humanoid rob…
Reinforcement Learning for Online Testing of Autonomous Driving Systems: a Replication and Extension Study
Luca Giamattei, Matteo Biagiola, Roberto Pietrantuono +2
In a recent study, Reinforcement Learning (RL) used in combination with many-objective search, has been shown to outperform alternative techniques (random search and many-objective…
Boundary State Generation for Testing and Improvement of Autonomous Driving Systems
Matteo Biagiola, Paolo Tonella
Recent advances in Deep Neural Networks (DNNs) and sensor technologies are enabling autonomous driving systems (ADSs) with an ever-increasing level of autonomy. However, assessing…
Neural Embeddings for Web Testing
Kasun Kanaththage, Luigi Libero Lucio Starace, Matteo Biagiola +2
Web test automation techniques often rely on crawlers to infer models of web applications for automated test generation. However, current crawlers rely on state equivalence algorit…
Testing of Deep Reinforcement Learning Agents with Surrogate Models
Matteo Biagiola, Paolo Tonella
Deep Reinforcement Learning (DRL) has received a lot of attention from the research community in recent years. As the technology moves away from game playing to practical contexts,…
Two is Better Than One: Digital Siblings to Improve Autonomous Driving Testing
Matteo Biagiola, Andrea Stocco, Vincenzo Riccio +1
Simulation-based testing represents an important step to ensure the reliability of autonomous driving software. In practice, when companies rely on third-party general-purpose simu…
Web Test Dependency Detection
Matteo Biagiola, Andrea Stocco, Ali Mesbah +2
E2E web test suites are prone to test dependencies due to the heterogeneous multi-tiered nature of modern web apps, which makes it difficult for developers to create isolated progr…