I’m Aryaz Eghbali, a PhD student in Software Lab at CISPA Helmholtz Center for Information Security, and the University of Stuttgart, in Germany. I work on automating software engineering processes by designing practical developer tools, frameworks, and metrics. I have been lucky to work under Prof. Dr. Michael Pradel's supervision.

Recent papers:

• Documentary: Natural Language-Focused Software Engineering via Code-Documentation Equivalence, FSE 2026
• PoCGen: Generating Proof-of-Concept Exploits for Vulnerabilities in npm Packages, FSE 2026
• DyLin: A Dynamic Linter for Python, FSE 2025 (You can use it in your CI/CD via auto-dylin GitHub action)
• De-Hallucinator: Mitigating LLM Hallucinations in Code Generation Tasks via Iterative Grounding, arXiv
• Using LLMs to generate unit tests (AKA TestPilot): An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation, IEEE Transactions on Software Engineering 2024

Other notable papers:

• DynaPyt: A Dynamic Analysis Framework for Python, ESEC/FSE 2022
• CrystalBLEU: Precisely and Efficiently Measuring the Similarity of Code, ASE 2022 (ACM SIGSOFT Distinguished Paper Award 🏆)

My Google Scholar Page.

Reach me at aryaz.egh@gmail.com