Aryaz Eghbali
PublicationsExperienceTalksServicesContact
Aryaz Eghbali

Aryaz Eghbali

PhD Student at CISPA Helmholtz Center for Information Security and University of Stuttgart, Germany

I am a researcher in the Software Lab focusing on automating software analysis and development.

Recently, I have been working on improving source code documentation by by introducing a novel attribute and a tool called Documentary to generate docstrings, an automated approach to generating proof-of-concept exploits for npm package vulnerabilities called PoCGen, a dynamic linter for Python called DyLin, mitigating hallucinations in LLM using iterative grounding, automatically generating tests, a novel metric to evaluate similarity in source code called CrystalBLEU, and the first general-purpose dynamic analysis framework for Python called DynaPyt.

My background includes work on distributed algorithms and distributed systems.

[email protected]

Publications

Natural Language-Focused Software Engineering via Code-Documentation Equivalence

Code

Aryaz Eghbali, Zhongxin Liu, Michael Pradel

FSE 2026

PoCGen: Generating Proof-of-Concept Exploits for npm Package Vulnerabilities

Deniz Simsek, Aryaz Eghbali, Michael Pradel

FSE 2026

DyLin: A Dynamic Linter for Python

Aryaz Eghbali, Felix Burk, Michael Pradel

FSE 2025

Mitigating LLM Hallucinations in Code Generation Tasks via Iterative Grounding

Aryaz Eghbali, Michael Pradel

arXiv 2024

An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation

Max Schäfer, Sarah Nadi, Aryaz Eghbali, Michael Pradel

TSE 2024

DynaPyt: A Dynamic Analysis Framework for Python

Aryaz Eghbali, Michael Pradel

ESEC/FSE 2022

CrystalBLEU: Precisely and Efficiently Measuring the Similarity of Code
ACM SIGSOFT Distinguished Paper Award

Aryaz Eghbali, Michael Pradel

ASE 2022

No Strings Attached: An Empirical Study of String-related Software Bugs

Aryaz Eghbali, Michael Pradel

ASE 2020

12 Angry Miners: A Heuristic-based Modeling of the BitCoin Mining Hardware Distribution Over Time

Aryaz Eghbali, Roger Wattenhofer

CBT 2019

Lower Bound for Abortable Leader Election

Aryaz Eghbali, Philipp Woelfel

DISC 2018

Experience

PhD in Computer Science
CISPA Helmholtz Center for Information Security

2026 - present

Supervisor: Michael Pradel

Working on AI- and program analysis-based developer tools.

PhD in Computer Science
University of Stuttgart

2020 - present

Supervisor: Michael Pradel

Working on AI- and program analysis-based developer tools.

Research Intern
GitHub

Summer 2022

Supervisor: Max Schaefer and Frank Tip

Worked on automated test generation

Researcher
ETH Zurich

2018 - 2019

Supervisor: Roger Wattenhofer

Worked on modeling the hardware usage by Bitcoin miners.

Data Science Intern
Divar.ir

Summer 2018

Worked on analyzing in-app chat data to detect spam and offensive messages.

M.Sc. in Computer Science
University of Calgary

2014 - 2018

Supervisor: Philipp Weolfel

Thesis on proving a lower bound for abortable leader election algorithm.

B.Sc. in Electrical & Computer Engineering
University of Tehran

2010 - 2014

Talks

Dynamically Analyzing Python Programs Using DynaPyt

ASE tutorial

2023

Iterative Code Completion Using Large Language Models

Dagstuhl Seminar on Programming Language Processing

2023

Services

Program Committee for ACM International Conference on AI-powered Software (AIware) 2026
Reviewer for IEEE Transactions on Software Engineering (TSE) 2026
Reviewer for ACM Transactions on Software Engineering and Methodology (TOSEM) 2025
Reviewer for IEEE Transactions on Software Engineering (TSE) 2024
Reviewer for Journal of Automated Software Engineering (ASE) 2024
Programme Committee for ASE Student Research Competition 2024
External reviewer for ISSTA 2024
Reviewer for Transactions on Interactive Intelligent Systems (TiiS) 2023