Chunyang Chen

Specifically, I apply AI, machine learning, NLP, and lightweight program analysis techniques in the following directions:

• AI(LLM)-assisted automated mobile app development including requirement elicitation [ICSE'19a, TSE'22], UI design [CSCW'19, CSCW'20, ICSE'21a], UI code generation [ICSE'18, TOSEM'20, FSE'20], app GUI testing [CHI'22, ICSE'23a, ICSE'23b], usability [ICSE'20a, ASE'20, ASE'22], accessibility testing [ICSE'20b, TSE'21], and bug replay [ICSE'22, ICSE'23, ICSE'24].
• AI-empowered mining software repositories including library/API migration [ASE'18a, TSE'19a], collaborative editing [CSCW'17, CSCW'18, CSCW'21], query reformulation [ASE'16, ICSE'21c], and thesaurus construction [ICSE'17, TSE'19].
• Robustness and security of deep learning and mobile apps including on-device model attack [ICSE'21-SEIP, TIFS'22], backdoor attack [ICSE'21d], phishing attack [TDSC'19], and deep learning defence [ASE'18, ISSTA'23].
• Agentic LLMs for software engineering and HCI including software testing [ICSE'23, ICSE'24a, ICSE'24b, TSE'24], bug replay [ISSTA'24, ICSE'24c, ICSE'24d], software accessibility [CHI'24], smart assistant development [UIST'24], and dataset construction [CHI'24]. All LLM-relevant works can be found on the dedicated page.

• 2026 Sep, we received the ACM SIGSOFT Distinguished Paper Award in ASE 2026 for “A11YRepair: Bridging Web Accessibility Barriers via Knowledge-Enhanced Divide-and-Conquer Repair”.
• 2026 Sep, our survey 'A Survey for LLM Agent Trajectory Analysis: From Failure Attribution to Enhancement' was accepted to IEEE Transactions on Software Engineering (TSE).
• 2026 Sep, we co-organize the 2026 LLM Software Development Winter School on 9-10 October at TUM IAS, co-located with ASE 2026.
• 2026 Jul, four papers were accepted at ASE 2026 (three research track, one industry showcase).
• 2026 Jul, two papers were accepted to ISSTA 2026: 'SEDCoT: Enhancing LLM-Based COBOL Code Translation via Symbolic Execution and Delta Debugging' and 'RippleGUItester: Change-Aware Exploratory Testing'.
• 2026 Apr, four papers were accepted at FSE 2026.
• 2026 Jan, we received the Gemini Academic Program Award from Google Cloud.
• 2025 Nov, we received the Amazon Research Award in Agentic AI track.
• 2025 Oct, we received the ACM SIGSOFT Distinguished Paper Award in ASE 2025 for “Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Repair”.

I am always looking for self-motivated PhD students with full scholarship through the open positions page, as well as long-term visiting scholars, postdocs and students. For master and bachelor students at TUM, we provide a list of thesis projects, please follow the instructions there.

For postdocs, I am happy to host and support applications through these fellowship schemes:

• Heilbronn AI Fellowship
• Humboldt Research Fellowship
• Marie Skłodowska-Curie Postdoctoral Fellowship
• TUM Global Postdoc Fellowship

• ACM SIGSOFT Distinguished Paper Award in ASE 2026 PDF
• Gemini Academic Program Award from Google Cloud
• ACM SIGSOFT Distinguished Paper Award in ASE 2025 PDF
• Amazon Research Award in AWS Agentic AI 2025
• Best Paper Honorable Mention in CHI 2024 PDF
• Discovery Early Career Researcher Award (DECRA) from Australian Research Council
• ACM SIGSOFT Early Career Researcher Award 2023
• ACM SIGSOFT Distinguished Paper Award in ICSE 2023 PDF
• ACM SIGSOFT Distinguished Paper Award in ICSE 2021 PDF
• Dean's Award for Research Impact (Economic and Social Impact) in Faculty of IT, Monash University
• Facebook Research Award in Probability and Programming 2020
• ACM SIGSOFT Distinguished Paper Award in ICSE 2020 PDF
• ACM SIGSOFT Distinguished Paper Award in ASE 2018 PDF
• Best Paper Award in SANER 2016 PDF
• Best Tool Demo in ASE 2016 PDF

1. [NeurIPS-26-D&B] SWE-Pro: A Benchmark for Evaluating LLMs on Performance-Oriented Repository-Level Optimization

   Advances in Neural Information Processing Systems, Evaluations and Datasets Track

   Ezgi Sarıkayak, Wenchao Gu, Hesham Ghonim, Chunyang Chen

   PDF
2. [TOSEM-26] Scenario-Guided LLM-based Mobile App GUI Testing

   ACM Transactions on Software Engineering and Methodology

   Shengcheng Yu, Yuchen Ling, Chunrong Fang, Quan Zhou, Yi Zhao, Chunyang Chen, Shaomin Zhu, Zhenyu Chen

   PDF
3. [EMSE-26] Guidelines for Empirical Studies in Software Engineering involving Large Language Models

   Springer Empirical Software Engineering

   Sebastian Baltes, Florian Angermeir, Chetan Arora, Marvin Muñoz Barón, Chunyang Chen, Lukas Böhme, Fabio Calefato, Neil Ernst, Davide Falessi, Brian Fitzgerald, Davide Fucci, Junda He, Christoph Treude, Marcos Kalinowski, Stefano Lambiase, Daniel Russo, Mircea Lungu, Cristina Martinez Montes, Lutz Prechelt, Paul Ralph, Rijnard van Tonder, Stefan Wagner

   PDF
4. [TSE-26] A Survey for LLM Agent Trajectory Analysis: From Failure Attribution to Enhancement

   IEEE Transactions on Software Engineering

   Junjie Wang, Yawen Wang, Mengzhuo Chen, Xiaofei Xie, Chunyang Chen, Fangwen Mu, Zhe Liu, Qing Wang

   PDF
5. [ASE-26] A11YRepair: Bridging Web Accessibility Barriers via Knowledge-Enhanced Divide-and-Conquer Repair

   IEEE/ACM International Conference on Automated Software Engineering

   Kai Huang, Ling Zhu, Jian Zhang, Xiaofei Xie, Chunyang Chen

   PDF · ACM SIGSOFT Distinguished Paper Award
6. [ASE-26] A Longitudinal Study of Android Apps Signing Key Protection

   IEEE/ACM International Conference on Automated Software Engineering

   Mark Huasong Meng, Qing Zhang, Weirao Lu, Chunyang Chen

   PDF
7. [ASE-26] Piece by Piece: Automating Combination Interaction GUI Testing via Planning and Dual Memory

   IEEE/ACM International Conference on Automated Software Engineering

   Zhe Liu, Oujin Wang, Junjie Wang, Chunyang Chen, Mengzhuo Chen, Boyu Wu, Yuekai Huang, Qing Wang

   To appear
8. [ISSTA-26] RippleGUItester: Change-Aware Exploratory Testing

   International Symposium on Software Testing and Analysis

   Yanqi Su, Michael Pradel, Chunyang Chen

   PDF
9. [ISSTA-26] SEDCoT: Enhancing LLM-Based COBOL Code Translation via Symbolic Execution and Delta Debugging

   International Symposium on Software Testing and Analysis

   Phillip Entin, Wenchao Gu, Alexander Knapp, Chunyang Chen

   To appear
10. [ACL-26-Finding] Beyond Neural Incompatibility: Cross-Scale Knowledge Transfer in Large Language Models through Latent Semantic Alignment

    Findings of the Association for Computational Linguistics

    Jian Gu, Aldeida Aleti, Chunyang Chen, Hongyu Zhang

    PDF
11. [FSE-26] ViBR: Automated Bug Replay from Video-based Reports Using Vision-Language Models

    ACM International Conference on the Foundations of Software Engineering

    Sidong Feng, Dingbang Wang, Nikola Tomic, Tingting Yu, Aldeida Aleti, Chunyang Chen

    PDF
12. [FSE-26] From Suspicious Signals to Crashes: Guiding Bug-driven GUI Testing via Code-inspired Tracing

    ACM International Conference on the Foundations of Software Engineering

    Mengzhuo Chen, Zhe Liu, Chunyang Chen, Junjie Wang, Boyu Wu, Yuekai Huang, Jun Hu, Qing Wang

    PDF forthcoming
13. [ICSE-26] Breaking Single-Tester Limits: Multi-Agent LLMs for Multi-User Feature Testing

    IEEE/ACM International Conference on Software Engineering

    Sidong Feng, Changhao Du, Huaxiao Liu, Qingnan Wang, Zhengwei Lv, Mengfei Wang, Chunyang Chen

    PDF
14. [ICSE-26] A Semantic-based Optimization Approach for Repairing LLMs: Case Study on Code Generation

    IEEE/ACM International Conference on Software Engineering

    Jian Gu, Aldeida Aleti, Chunyang Chen, Hongyu Zhang

    PDF
15. [ICSE-26] Repair Ingredients Are All You Need: Improving Large Language Model-Based Program Repair via Repair Ingredients Search

    IEEE/ACM International Conference on Software Engineering

    Jiayi Zhang, Kai Huang, Jian Zhang, Yang Liu, Chunyang Chen

    PDF
16. [ICSE-26] Think Outside the Box: Automating Inter-App Functionality Testing via Memory Implanting and Reasoning

    IEEE/ACM International Conference on Software Engineering

    Mengzhuo Chen, Zhe Liu, Chunyang Chen, Junjie Wang, Yangguang Xue, Boyu Wu, Libin Wu, Qing Wang

    PDF forthcoming
17. [TSE-24] Software Testing with Large Language Model: Survey, Landscape, and Vision

    IEEE Transactions on Software Engineering

    Junjie Wang, Yuchao Huang, Chunyang Chen, Zhe Liu, Song Wang, Qing Wang

    PDF

See more papers in the full list, and recent LLM-related works on the LLM publications page.

• CITHN2015 - AI coding: modern software development, TUM (2026-now)
• CITHN2014 / CITHN4004 - Foundations and Application of Generative AI, TUM (2024-now)
• CITHN3003 - Advanced Topics on Software Engineering, TUM (2024-now)
• INHN0015 - Seminar Automated Mobile App Testing, TUM (2024)
• FIT3170 - Software Engineering Practice, Monash (2021-2023)
• FIT9136 - Algorithms and Programming Foundations in Python, Monash (2020)
• FIT9133 - Programming Foundations in Python, Monash (2019)
• CZ3003 - Software Systems Analysis & Design, NTU (2015-2017)
• CE2006 - Software Engineering, NTU (2016)
• CZ2002 - Object-Oriented Design & Programming, NTU (2016)