Publications

My work spans software verification, neural bug detection, and AI-assisted software engineering. See my research overview for an introduction to these topics.

Google Scholar · DBLP

Conference, Workshop, and Journal Publications

2026

• Round-Trip Mutation Testing: Translating Code to Natural Language Intent and back

  Asma Hamidi, Cedric Richter, Ahmed Khanfir, Mike Papadakis

  International Workshop on Mutation Analysis (Mutation), ICST Workshops, 2026

  Author version

2025

• Cooperative Software Verification via Dynamic Program Splitting

  Cedric Richter, Marek Chalupa, Marie-Christine Jakobs, Heike Wehrheim

  International Conference on Software Engineering (ICSE), 2025

  PDF Artifact

• Construction of verifier combinations from off-the-shelf components

  Dirk Beyer, Sudeep Kanav, Tobias Kleinert, Cedric Richter

  Formal Methods in System Design, 2025

• BUBAAK: Dynamic Cooperative Verification

  Marek Chalupa, Cedric Richter

  Tools and Algorithms for the Construction and Analysis of Systems (TACAS), 2025 · Competition contribution

2024

• Can ChatGPT support software verification?

  Christian Janßen, Cedric Richter, Heike Wehrheim

  Fundamental Approaches to Software Engineering (FASE), 2024

  Author version

• Bubaak-SpLit: Split what you cannot verify

  Marek Chalupa, Cedric Richter

  Tools and Algorithms for the Construction and Analysis of Systems (TACAS), 2024 · Competition contribution

• Parallel program analysis on path ranges

  Jan Haltermann, Marie-Christine Jakobs, Cedric Richter, Heike Wehrheim

  Science of Computer Programming, 2024

  Author version

2023

• How to Train Your Neural Bug Detector: Artificial vs Real Bugs

  Cedric Richter, Heike Wehrheim

  International Conference on Automated Software Engineering (ASE), 2023

  PDF Code

• Robustness Testing of Software Verifiers

  Florian Dyck, Cedric Richter, Heike Wehrheim

  Software Engineering and Formal Methods (SEFM), 2023

• Ranged Program Analysis via Instrumentation

  Jan Haltermann, Marie-Christine Jakobs, Cedric Richter, Heike Wehrheim

  Software Engineering and Formal Methods (SEFM), 2023

• Parallel Program Analysis via Range Splitting

  Jan Haltermann, Marie-Christine Jakobs, Cedric Richter, Heike Wehrheim

  Fundamental Approaches to Software Engineering (FASE), 2023

2022

• Are Neural Bug Detectors Comparable to Software Developers on Variable Misuse Bugs?

  Cedric Richter, Jan Haltermann, Marie-Christine Jakobs, Felix Pauck, Stefan Schott, Heike Wehrheim

  International Conference on Automated Software Engineering (ASE), 2022

• Learning Realistic Mutations: Bug Creation for Neural Bug Detectors

  Cedric Richter, Heike Wehrheim

  International Conference on Software Testing, Verification and Validation (ICST), 2022

• TSSB-3M: Mining Single Statement Bugs at Massive Scale

  Cedric Richter, Heike Wehrheim

  International Conference on Mining Software Repositories (MSR), 2022 · Data and Tool Showcase

  Author version

• Construction of Verifier Combinations Based on Off-the-Shelf Verifiers

  Dirk Beyer, Sudeep Kanav, Cedric Richter

  Fundamental Approaches to Software Engineering (FASE), 2022

2021

• CoVeriTest with Adaptive Time Scheduling

  Marie-Christine Jakobs, Cedric Richter

  Fundamental Approaches to Software Engineering (FASE), 2021 · Competition contribution

2020

• Attend and Represent: A Novel View on Algorithm Selection for Software Verification

  Cedric Richter, Heike Wehrheim

  International Conference on Automated Software Engineering (ASE), 2020

• Algorithm selection for software validation based on graph kernels

  Cedric Richter, Eyke Hüllermeier, Marie-Christine Jakobs, Heike Wehrheim

  Automated Software Engineering, 2020

2019

• PeSCo: Predicting Sequential Combinations of Verifiers

  Cedric Richter, Heike Wehrheim

  Tools and Algorithms for the Construction and Analysis of Systems (TACAS), 2019 · Competition contribution

Preprints

These manuscripts are available on arXiv; they are listed separately from conference and journal publications.

2026

• On the Risks of using LLM-Generated Tests for Regression Testing

  Mohammadali Charoosaei, Cedric Richter, Mike Papadakis

  arXiv:2610.11835, 2026

• Automatically Evolving Prompt Guidelines for Task-Specific Optimization

  Cedric Richter, Salah Ghamizi, Mike Papadakis

  arXiv:2607.14105, 2026

• From Failing to Passing: Evolving Natural Language Prompt Optimization Rules for LLM Code Generation

  Amal Akli, Melissa Akli, Cedric Richter, Mike Papadakis, Yves Le Traon

  arXiv:2607.05121, 2026

• Prompt Coverage Adequacy

  Florian Tambon, Michael Konstantinou, Cedric Richter, Charles Chenouard, Mark Harman, Mike Papadakis

  arXiv:2607.02057, 2026

• Underspecification does not imply Incoherence: The Risks of Semantic Collapse in Coding Models

  Cedric Richter, Mike Papadakis

  arXiv:2607.01953, 2026

2025

• Beyond Postconditions: Can Large Language Models infer Formal Contracts for Automatic Software Verification?

  Cedric Richter, Heike Wehrheim

  arXiv:2510.12702, 2025

Doctoral Thesis

• Neural Bug Detection

  Cedric Richter

  PhD thesis, University of Oldenburg, 2025

  PDF