4 papers
Understanding Agent-Reactive Bugs at the Model-Harness Boundary: An Empirical Study of LLM Agent Issue Reports
Jingyi Chen, Songqiang Chen, Hengcheng Zhu +3
LLM agents span command-line interfaces (e.g., Codex) and agent frameworks (e.g., LangChain), integrating backend LLMs with harness code that parses model outputs, controls agent l…
Can Emulating Semantic Translation Help LLMs with Code Translation? A Study Based on Pseudocode
Songqiang Chen, Congying Xu, Jingyi Chen +3
Although large language models (LLMs) show promising potential in code translation, they still struggle to generate accurate translations using the commonly adopted direct code-to-…
Multi-Agent Systems for Dataset Adaptation in Software Engineering: Capabilities, Limitations, and Future Directions
Jingyi Chen, Xiaoyan Guo, Songqiang Chen +2
Automating the adaptation of software engineering (SE) research artifacts across datasets is essential for scalability and reproducibility, yet it remains largely unstudied. Recent…
When LLMs Meet API Documentation: Can Retrieval Augmentation Aid Code Generation Just as It Helps Developers?
Jingyi Chen, Songqiang Chen, Jialun Cao +2
Retrieval-augmented generation (RAG) has increasingly shown its power in extending large language models' (LLMs') capability beyond their pre-trained knowledge. Existing works have…