24 citations · 58 across the 21 of their papers we have counts for
21 papers
Generation of Web Apps with Agentic IDEs: An Empirical Assessment
Manuel Marceca, Maria Teresa Rossi, Leonardo Mariani
Agentic IDEs are among the most significant innovations in software engineering, aiming to accelerate application development through LLM-based agents that can assist developers du…
An Evaluation of Role-Based Multi-Agent Code Generation on Repository-Scale Problems
Benedetta Donato, Noah Hagar-Dent, Aaron Worsnop +2
Role-based multiagent code generation aims to make LLMs more effective on repository-scale problems, moving beyond small programming tasks. We evaluate this approach on 12 Java rep…
GreenServ: Energy-Efficient Context-Aware Dynamic Routing for Multi-Model LLM Inference
Thomas Ziller, Shashikant Ilager, Alessandro Tundo +3
Large language models (LLMs) demonstrate remarkable capabilities, but their broad deployment is limited by significant computational resource demands, particularly energy consumpti…
"Where is My Troubleshooting Procedure?": Studying the Potential of RAG in Assisting Failure Resolution of Large Cyber-Physical System
Maria Teresa Rossi, Leonardo Mariani, Oliviero Riganelli +3
In today's complex industrial environments, operators must often navigate through extensive technical manuals to identify troubleshooting procedures that may help react to some obs…
Coverage-Guided Road Selection and Prioritization for Efficient Testing in Autonomous Driving Systems
Qurban Ali, Andrea Stocco, Leonardo Mariani +1
Autonomous Driving Assistance Systems (ADAS) rely on extensive testing to ensure safety and reliability, yet road scenario datasets often contain redundant cases that slow down the…
Towards Multi-Platform Mutation Testing of Task-based Chatbots
Diego Clerissi, Elena Masserini, Daniela Micucci +1
Chatbots, also known as conversational agents, have become ubiquitous, offering services for a multitude of domains. Unlike general-purpose chatbots, task-based chatbots are softwa…
Bug Whispering: Towards Audio Bug Reporting
Elena Masserini, Daniela Micucci, Leonardo Mariani
Bug reporting is a key feature of mobile applications, as it enables developers to collect information about faults that escaped testing and thus affected end-users. This paper exp…
From PREVENTion to REACTion: Enhancing Failure Resolution in Naval Systems
Maria Teresa Rossi, Leonardo Mariani, Oliviero Riganelli
Complex and large industrial systems often misbehave, for instance, due to wear, misuse, or faults. To cope with these incidents, it is important to timely detect their occurrences…
Towards the Assessment of Task-based Chatbots: From the TOFU-R Snapshot to the BRASATO Curated Dataset
Elena Masserini, Diego Clerissi, Daniela Micucci +2
Task-based chatbots are increasingly being used to deliver real services, yet assessing their reliability, security, and robustness remains underexplored, also due to the lack of l…
MultiMind: A Plug-in for the Implementation of Development Tasks Aided by AI Assistants
Benedetta Donato, Leonardo Mariani, Daniela Micucci +2
The integration of AI assistants into software development workflows is rapidly evolving, shifting from automation-assisted tasks to collaborative interactions between developers a…
OpenCat: Improving Interoperability of ADS Testing
Qurban Ali, Andrea Stocco, Leonardo Mariani +1
Testing Advanced Driving Assistance Systems (ADAS), such as lane-keeping functions, requires creating road topologies or using predefined benchmarks. However, the test cases in exi…
Studying How Configurations Impact Code Generation in LLMs: the Case of ChatGPT
Benedetta Donato, Leonardo Mariani, Daniela Micucci +1
Leveraging LLMs for code generation is becoming increasingly common, as tools like ChatGPT can suggest method implementations with minimal input, such as a method signature and bri…
On the Possibility of Breaking Copyleft Licenses When Reusing Code Generated by ChatGPT
Gaia Colombo, Leonardo Mariani, Daniela Micucci +1
AI assistants can help developers by recommending code to be included in their implementations (e.g., suggesting the implementation of a method from its signature). Although useful…
Testing in the Evolving World of DL Systems:Insights from Python GitHub Projects
Qurban Ali, Oliviero Riganelli, Leonardo Mariani
In the ever-evolving field of Deep Learning (DL), ensuring project quality and reliability remains a crucial challenge. This research investigates testing practices within DL proje…
ReProbe: An Architecture for Reconfigurable and Adaptive Probes
Federico Alessi, Alessandro Tundo, Marco Mobilio +2
Modern distributed systems are highly dynamic and scalable, requiring monitoring solutions that can adapt to rapid changes. Monitoring systems that rely on external probes can only…
Towards Model-Driven Dashboard Generation for Systems-of-Systems
Maria Teresa Rossi, Alessandro Tundo, Leonardo Mariani
Configuring and evolving dashboards in complex and large-scale Systems-of-Systems (SoS) can be an expensive and cumbersome task due to the many Key Performance Indicators (KPIs) th…
Assessing AI-Based Code Assistants in Method Generation Tasks
Vincenzo Corso, Leonardo Mariani, Daniela Micucci +1
AI-based code assistants are increasingly popular as a means to enhance productivity and improve code quality. This study compares four AI-based code assistants, GitHub Copilot, Ta…
Generating Java Methods: An Empirical Assessment of Four AI-Based Code Assistants
Vincenzo Corso, Leonardo Mariani, Daniela Micucci +1
AI-based code assistants are promising tools that can facilitate and speed up code development. They exploit machine learning algorithms and natural language processing to interact…
Analyzing Prompt Influence on Automated Method Generation: An Empirical Study with Copilot
Ionut Daniel Fagadau, Leonardo Mariani, Daniela Micucci +1
Generative AI is changing the way developers interact with software systems, providing services that can produce and deliver new content, crafted to satisfy the actual needs of dev…
Anonymizing Test Data in Android: Does It Hurt?
Elena Masserini, Davide Ginelli, Daniela Micucci +2
Failure data collected from the field (e.g., failure traces, bug reports, and memory dumps) represent an invaluable source of information for developers who need to reproduce and a…
Supporting Early-Safety Analysis of IoT Systems by Exploiting Testing Techniques
Diego Clerissi, Juri Di Rocco, Davide Di Ruscio +6
IoT systems complexity and susceptibility to failures pose significant challenges in ensuring their reliable operation Failures can be internally generated or caused by external fa…