About Me

I am a final year Computer Science PhD student at UIUC advised by Lingming Zhang. My research interest lies in the intersection of Machine Learning and Software Engineering. In my PhD study, I am supported by the Amazon Science Ph.D. Fellowship.

Before coming to UIUC, I completed my undergrad at the University of Toronto where I was fortunate to work with Natalie Enright Jerger, David Lie, Nicolas Papernot, and Shurui Zhou.

📢 I am on the tenure track faculty and industry research scientist job markets (2025-26) seeking positions in Computer Science.

Selected Publications

• Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly? Preprint
  Chunqiu Steven Xia, Zhe Wang, Yan Yang, Yuxiang Wei, Lingming Zhang | Nov, 2025.
  First live AI software agent that continuously evolve itself on-the-fly to solve real-world software problems;
  🏅 Top-1 open-source agent on SWE-bench Verified (79.2%) and SWE-Bench Pro (45.8%)
  [ preprint | webpage ]
  
• Agentless 😺: Demystifying LLM-based Software Engineering Agents In Proceedings of 33rd ACM SIGSOFT International Symposium on the Foundations of Software Engineering (FSE 2025)
  Chunqiu Steven Xia*, Yinlin Deng*, Soren Dunn, Lingming Zhang | June, 2025.
  🏆 Selected as an ACM SIGSOFT distinguished paper;
  Adopted by OpenAI, Meta, DeepSeek, etc to evaluate their recent models and build custom agent scaffolds
  
  [ preprint ]
  
• Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT In Proceedings of the 33rd International Symposium on Software Testing and Analysis (ISSTA 2024)
  Chunqiu Steven Xia and Lingming Zhang | Sep, 2024.
  [ preprint ]
• Fuzz4All: Universal Fuzzing with Large Language Models In Proceedings of the 46th IEEE/ACM International Conference on Software Engineering (ICSE 2024)
  Chunqiu Steven Xia, Matteo Paltenghi, Jia Le Tian, Michael Pradel, Lingming Zhang | April, 2024.
  [ preprint | webpage ]
• Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM In Proceedings of the 1st Conference on Language Modeling (COLM 2024)
  Chunqiu Steven Xia*, Yinlin Deng*, Lingming Zhang | March, 2024.
  🏆 Selected as an oral spotlight
  [ preprint | webpage ]
• Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation In Proceedings of the 37th Annual Conference on Neural Information Processing Systems (NeurIPS 2023)
  Jiawei Liu*, Chunqiu Steven Xia*, Yuyao Wang, Lingming Zhang | Dec, 2023.
  1M dataset downloads; integrated by various major companies
  [ preprint ]
• Large Language Models are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models In Proceedings of the 32nd International Symposium on Software Testing and Analysis (ISSTA 2023)
  Yinlin Deng, Chunqiu Steven Xia, Haoran Peng, Chenyuan Yang, Lingming Zhang | July, 2023.
  [ preprint ]
• Automated Program Repair in the Era of Large Pre-trained Language Models In Proceedings of the 45th IEEE/ACM International Conference on Software Engineering (ICSE 2023)
  Chunqiu Steven Xia, Yuxiang Wei, Lingming Zhang | May, 2023.
  [ preprint ]
• Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learning In Proceedings of 30th ACM SIGSOFT International Symposium on the Foundations of Software Engineering (FSE 2022)
  Chunqiu Steven Xia and Lingming Zhang | Nov, 2022.
  [ paper ]

Invited Talks

• South Park Commons AI Agent Speaker Series: Agentless 😺: Demystifying LLM-based Software Engineering Agents
• Alibaba Tongyi Lab: Agents & LLMs for Software Development
• SecurityFrontiers.AI: Universal Fuzzing with Large Language Models
• GAI4SE @ NC State University: LLMs for Program Repair, Fuzzing and Testing
• Kwai Inc: Universal Fuzzing with Large Language Models
• Computer Security Group @ Ohio State University: Are Large Language Models Effective Fuzzers?
• Uber Programming Systems Team: Leveraging Large Language Models for Automated Program Repair ... and other Software Engineering tasks
• Microsoft Data&AI: Leveraging Large Language Models for Software Engineering Tasks
• Software Lab @ University of Stuttgart: Automated Program Repair in the era of Large Language Models

Services

• PC Member: ASE'25
• PC Member: FORGE@ICSE'25, APR@ICSE'25, APR@ICSE'24
• Conference Reviewer: ICLR'26, NeurIPS'25, COLM'25, ICLR'25, NeurIPS'24
• Journal Reviewer: TOSEM, TSE

website template shamelessly taken from Deian Stefan

Publications

Below is the list of my complete publications. Google Scholar also provides such list

• Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly? Preprint
  Chunqiu Steven Xia, Zhe Wang, Yan Yang, Yuxiang Wei, Lingming Zhang | Nov, 2025.
  First live AI software agent that continuously evolve itself on-the-fly to solve real-world software problems;
  🏅 Top-1 open-source agent on SWE-bench Verified (79.2%) and SWE-Bench Pro (45.8%)
  [ preprint | webpage ]
  
• Agentless 😺: Demystifying LLM-based Software Engineering Agents In Proceedings of 33rd ACM SIGSOFT International Symposium on the Foundations of Software Engineering (FSE 2025)
  Chunqiu Steven Xia*, Yinlin Deng*, Soren Dunn, Lingming Zhang | June, 2025.
  🏆 Selected as an ACM SIGSOFT distinguished paper;
  Adopted by OpenAI, Meta, DeepSeek, etc to evaluate their recent models and build custom agent scaffolds
  
  [ preprint ]
  
• Can LLMs Implicitly Learn Numeric Parameter Constraints in Data Science APIs? In Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024)
  Yinlin Deng, Chunqiu Steven Xia, Zhezhen Cao, Meiziniu Li, Lingming Zhang | Dec, 2024.
  [ preprint ]
• Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT In Proceedings of the 33rd International Symposium on Software Testing and Analysis (ISSTA 2024)
  Chunqiu Steven Xia and Lingming Zhang | Sep, 2024.
  [ preprint ]
• Fuzz4All: Universal Fuzzing with Large Language Models In Proceedings of the 46th IEEE/ACM International Conference on Software Engineering (ICSE 2024)
  Chunqiu Steven Xia, Matteo Paltenghi, Jia Le Tian, Michael Pradel, Lingming Zhang | April, 2024.
  [ preprint | webpage ]
• Large Language Models are Edge-Case Fuzzers: Testing Deep Learning Libraries via FuzzGPT In Proceedings of the 46th IEEE/ACM International Conference on Software Engineering (ICSE 2024)
  Yinlin Deng, Chunqiu Steven Xia, Chenyuan Yang, Shizhuo Dylan Zhang, Shujing Yang, Lingming Zhang | April, 2024.
  [ preprint ]
• Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM In Proceedings of the 1st Conference on Language Modeling (COLM 2024)
  Chunqiu Steven Xia*, Yinlin Deng*, Lingming Zhang | March, 2024.
  🏆 Selected as an oral spotlight
  [ preprint | webpage ]
• Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair In Proceedings of the 31th ACM SIGSOFT International Symposium on the Foundations of Software Engineering (FSE 2023)
  Yuxiang Wei, Chunqiu Steven Xia, Lingming Zhang | Dec, 2023.
  🏆 Selected as a CACM Research Highlight
  [ preprint | code ]
• Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation In Proceedings of the 37th Annual Conference on Neural Information Processing Systems (NeurIPS 2023)
  Jiawei Liu*, Chunqiu Steven Xia*, Yuyao Wang, Lingming Zhang | Dec, 2023.
  1M dataset downloads; integrated by various major companies
  [ preprint ]
• The Plastic Surgery Hypothesis in the Era of Large Language Models In Proceedings of the 38th IEEE/ACM International Conference on Automated Software Engineering (ASE 2023)
  Chunqiu Steven Xia, Yifeng Ding, Lingming Zhang | Sep, 2023.
  [ preprint | code ]
• Large Language Models are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models In Proceedings of the 32nd International Symposium on Software Testing and Analysis (ISSTA 2023)
  Yinlin Deng, Chunqiu Steven Xia, Haoran Peng, Chenyuan Yang, Lingming Zhang | July, 2023.
  [ preprint ]
• Automated Program Repair in the Era of Large Pre-trained Language Models In Proceedings of the 45th IEEE/ACM International Conference on Software Engineering (ICSE 2023)
  Chunqiu Steven Xia, Yuxiang Wei, Lingming Zhang | May, 2023.
  [ preprint | code ]
• Balancing Effectiveness and Flakiness of Non-Deterministic Machine Learning Tests In Proceedings of the 45th IEEE/ACM International Conference on Software Engineering (ICSE 2023)
  Chunqiu Steven Xia, Saikat Dutta, Sasa Misailovic, Darko Marinov, Lingming Zhang | May, 2023.
  [ paper | code ]
• Conversational Automated Program Repair
  Chunqiu Steven Xia and Lingming Zhang | Jan, 2023.
  [ preprint ]
• Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learning In Proceedings of the 30th ACM SIGSOFT International Symposium on the Foundations of Software Engineering (FSE 2022)
  Chunqiu Steven Xia and Lingming Zhang | Nov, 2022.
  [ paper | code ]
• A Large Scale Study of User Behavior, Expectations and Engagement with Android Permissions In Proceedings of the 30th USENIX Security Symposium (USENIX 2021)
  Weicheng Cao, Chunqiu Steven Xia, Sai Teja Peddinti, David Lie, Nina Taft, Lisa M. Austin | Aug, 2021.
  [ paper ]
• The eh model: Early design space exploration of intermittent processor architectures In Proceedings of the 51st Annual IEEE/ACM International Symposium on Microarchitecture (MICRO 2018)
  Joshua San Miguel, Karthik Ganesan, Mario Badr, Chunqiu Steven Xia, Rose Li, Hsuan Hsiao, Natalie Enright Jerger | Oct, 2018.
  [ paper ]