Chunqiu Steven Xia

27 papers A* 8A 2Journal 15Unranked 2

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Demystifying LLM-Based Software Engineering Agents. Proc. ACM Softw. Eng. Chunqiu Steven Xia, Yinlin Deng, Soren Dunn, Lingming Zhang
2025	J	`jnl`	Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly? CoRR Chunqiu Steven Xia, Zhe Wang, Yan Yang, Yuxiang Wei, Lingming Zhang
2025	A*	`conf`	UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debugging. EMNLP Cheryl Lee, Chunqiu Steven Xia, Longji Yang, Jen-tse Huang, Zhouruixin Zhu, Lingming Zhang, Michael R. Lyu
2024	J	`jnl`	A Unified Debugging Approach via LLM-Based Multi-Agent Synergy. CoRR Cheryl Lee, Chunqiu Steven Xia, Jen-tse Huang, Zhouruixin Zhu, Lingming Zhang, Michael R. Lyu
2024	J	`jnl`	Agentless: Demystifying LLM-based Software Engineering Agents. CoRR Chunqiu Steven Xia, Yinlin Deng, Soren Dunn, Lingming Zhang
2024	A	`conf`	Automated Program Repair via Conversation: Fixing 162 out of 337 Bugs for $0.42 Each using ChatGPT. ISSTA Chunqiu Steven Xia, Lingming Zhang
2024	A*	`conf`	Can LLMs Implicitly Learn Numeric Parameter Constraints in Data Science APIs? NeurIPS Yinlin Deng, Chunqiu Steven Xia, Zhezhen Cao, Meiziniu Li, Lingming Zhang
2024	A*	`conf`	Fuzz4All: Universal Fuzzing with Large Language Models. ICSE Chunqiu Steven Xia, Matteo Paltenghi, Jia Le Tian, Michael Pradel, Lingming Zhang
2024	A*	`conf`	Large Language Models are Edge-Case Generators: Crafting Unusual Programs for Fuzzing Deep Learning Libraries. ICSE Yinlin Deng, Chunqiu Steven Xia, Chenyuan Yang, Shizhuo Dylan Zhang, Shujing Yang, Lingming Zhang
2024	J	`jnl`	Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM. CoRR Chunqiu Steven Xia, Yinlin Deng, Lingming Zhang
2023	A*	`conf`	Automated Program Repair in the Era of Large Pre-trained Language Models. ICSE Chunqiu Steven Xia, Yuxiang Wei, Lingming Zhang
2023	A*	`conf`	Balancing Effectiveness and Flakiness of Non-Deterministic Machine Learning Tests. ICSE Chunqiu Steven Xia, Saikat Dutta, Sasa Misailovic, Darko Marinov, Lingming Zhang
2023	J	`jnl`	Conversational Automated Program Repair. CoRR Chunqiu Steven Xia, Lingming Zhang
2023	—	`conf`	Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair. ESEC/SIGSOFT FSE Yuxiang Wei, Chunqiu Steven Xia, Lingming Zhang
2023	J	`jnl`	Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair. CoRR Yuxiang Wei, Chunqiu Steven Xia, Lingming Zhang
2023	A*	`conf`	Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation. NeurIPS Jiawei Liu, Chunqiu Steven Xia, Yuyao Wang, Lingming Zhang
2023	J	`jnl`	Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation. CoRR Jiawei Liu, Chunqiu Steven Xia, Yuyao Wang, Lingming Zhang
2023	J	`jnl`	Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT. CoRR Chunqiu Steven Xia, Lingming Zhang
2023	A	`conf`	Large Language Models Are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models. ISSTA Yinlin Deng, Chunqiu Steven Xia, Haoran Peng, Chenyuan Yang, Lingming Zhang
2023	J	`jnl`	Large Language Models are Edge-Case Fuzzers: Testing Deep Learning Libraries via FuzzGPT. CoRR Yinlin Deng, Chunqiu Steven Xia, Chenyuan Yang, Shizhuo Dylan Zhang, Shujing Yang, Lingming Zhang
2023	J	`jnl`	Revisiting the Plastic Surgery Hypothesis via Large Language Models. CoRR Chunqiu Steven Xia, Yifeng Ding, Lingming Zhang
2023	A*	`conf`	The Plastic Surgery Hypothesis in the Era of Large Language Models. ASE Chunqiu Steven Xia, Yifeng Ding, Lingming Zhang
2023	J	`jnl`	Universal Fuzzing via Large Language Models. CoRR Chunqiu Steven Xia, Matteo Paltenghi, Jia Le Tian, Michael Pradel, Lingming Zhang
2022	J	`jnl`	Fuzzing Deep-Learning Libraries via Large Language Models. CoRR Yinlin Deng, Chunqiu Steven Xia, Haoran Peng, Chenyuan Yang, Lingming Zhang
2022	J	`jnl`	Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learning. CoRR Chunqiu Steven Xia, Lingming Zhang
2022	—	`conf`	Less training, more repairing please: revisiting automated program repair via zero-shot learning. ESEC/SIGSOFT FSE Chunqiu Steven Xia, Lingming Zhang
2022	J	`jnl`	Practical Program Repair in the Era of Large Pre-trained Language Models. CoRR Chunqiu Steven Xia, Yuxiang Wei, Lingming Zhang