25 citations · 66 across the 7 of their papers we have counts for
7 papers
Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution
Kai Yu, Zhenhao Zhou, Junhao Zeng +8
Repository-level issue resolution benchmarks have become a standard testbed for evaluating LLM-based agents, yet success is still predominantly measured by test pass rates. In prac…
Towards Iterative End-to-End Software Development: A Feature-Driven Multi-Agent Framework
Junwei Liu, Chen Xu, Chong Wang +5
Recent advances in large language model agents offer the promise of automating end-to-end software development from natural language requirements. However, existing approaches larg…
Can Agents Fix Agent Issues?
Alfin Wijaya Rahardja, Junwei Liu, Weitong Chen +2
LLM-based agent systems are emerging as a new software paradigm and have been widely adopted across diverse domains such as medicine, robotics, and programming. However, maintainin…
Large Language Model-Based Agents for Software Engineering: A Survey
Junwei Liu, Kaixin Wang, Yixuan Chen +4
The recent advance in Large Language Models (LLMs) has shaped a new paradigm of AI agents, i.e., LLM-based agents. Compared to standalone LLMs, LLM-based agents substantially exten…
STALL+: Boosting LLM-based Repository-level Code Completion with Static Analysis
Junwei Liu, Yixuan Chen, Mingwei Liu +2
Repository-level code completion is challenging as it involves complicated contexts from multiple files in the repository. To date, researchers have proposed two technical categori…
ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation
Xueying Du, Mingwei Liu, Kaixin Wang +7
In this work, we make the first attempt to evaluate LLMs in a more challenging code generation scenario, i.e. class-level code generation. We first manually construct the first cla…
Evaluating Instruction-Tuned Large Language Models on Code Comprehension and Generation
Zhiqiang Yuan, Junwei Liu, Qiancheng Zi +3
In this work, we evaluate 10 open-source instructed LLMs on four representative code comprehension and generation tasks. We have the following main findings. First, for the zero-sh…