Annibale Panichella

Annibale Panichella

Associate Professor

Delft University of Technology

Biography

I am an Associate Professor in the Software Engineering Research Group (SERG) at Delft University of Technology (TU Delft) in the Netherlands. Within SERG, I lead the Computation Intelligence for Software Engineering Lab (CISELab), where my research focuses on software testing, search-based software engineering, AI for software engineering, software testing for AI-enabled systems, and empirical software engineering.

I serve as the track lead for “Testing for and with AI” within AI4SE, TU Delft’s ICAI lab on AI for Software Engineering, funded by JetBrains. I am also involved in the FUSE Lab, a collaborative research initiative co-sponsored by Meta’s DevInfra team and TU Delft, focusing on the reliability, testing, and evolution of modern software systems. In addition, I am the principal investigator of the UBRI program at TU Delft. My research has been supported by national and international funding programs, including the European Commission’s Horizon 2020 projects on test amplification (STAMP) and testing for cyber-physical systems (COSMOS).

I have co-authored more than 130 peer-reviewed publications in leading software engineering and evolutionary computation journals and conferences. My research has contributed to advances in automated software testing, search-based software engineering, software quality assurance, and the engineering and testing of AI-enabled systems. I am grateful to have received the Most Influential Paper Awards at SANER 2024 and ICST 2025, as well as Best Paper Awards at ICPC, SBFT, and SSBSE.

I actively contribute to the software engineering research community through service in major conferences and journals. I regularly serve on program committees of leading conferences, including ICSE, ESEC/FSE, ASE, ISSTA, ICST, and GECCO, and review for journals such as IEEE Transactions on Software Engineering (TSE), ACM Transactions on Software Engineering and Methodology (TOSEM), Empirical Software Engineering (EMSE), IEEE Transactions on Evolutionary Computation (TEVC), and Software Testing, Verification and Reliability (STVR).

Interests
  • Search-Based and AI-Driven Software Engineering
  • Automated Test Generation and Fuzzing
  • Testing of AI-Enabled and LLM-Based Systems
  • Large Language Models for Code
  • Automated Program Repair
  • Sustainable and Green AI for Software Engineering
  • Testing of Autonomous and Cyber-Physical Systems
  • Security and Regression Testing
  • Empirical Software Engineering
  • Evolutionary Computation
Education
  • PhD in Software Engineering

    University of Salerno

Experience

 
 
 
 
 
Fondazione Bruno Kessler - Security & Trust
Scientific Developer
January 2014 – December 2014 Trento, Italy
 
 
 
 
 
Delft University of Technology
Post-doc
January 2015 – September 2016 Delft, The Netherlands
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Delft University of Technology
Assistant Professor
March 2018 – December 2022 Delft, The Netherlands
 
 
 
 
 
Delft University of Technology
Associate Professor
January 2023 – Present Delft, The Netherlands

Recent Publications

Quickly discover relevant content by filtering publications.
(2026). What Challenges Do Developers Face in AI Agent Systems? An Empirical Study on Stack Overflow & GitHub Issues. Journal of Systems and Software (JSS).

(2026). Beyond FLOPs: Energy-Aware Knowledge Distillation for Sustainable LLMs on Code-Related Tasks. The ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM 2026).

Preprint

(2026). Test Case Selection for Deep Neural Networks: A Replication Study on LLMs for Code (Replicability Study). The ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2026).

(2026). A Metamorphic Testing Approach to Diagnosing Memorization in LLM-Based Program Repair. The 26th IEEE International Conference on Software Quality, Reliability, and Security (QRS 2026).

(2026). Agentic Based Python Dependency Resolution. ACM International Conference on AI-powered Software - Competition Track (AIware 2026).