14 papers
TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Code
Jiangping Huang, Wenguang Ye, Weisong Sun +3
Large Language Models (LLMs) often generate code with subtle but critical bugs, especially for complex tasks. Existing automated repair methods typically rely on superficial pass/f…
REprompt: Prompt Generation for Intelligent Software Development Guided by Requirements Engineering
Junjie Shi, Weisong Sun, Zhenpeng Chen +4
The rapid development of large language models is transforming software development. Beyond serving as code auto-completion tools in integrated development environments, large lang…
Hallucination Detection for LLM-based Text-to-SQL Generation via Two-Stage Metamorphic Testing
Bo Yang, Yinfen Xia, Weisong Sun +1
In Text-to-SQL generation, large language models (LLMs) have shown strong generalization and adaptability. However, LLMs sometimes generate hallucinations, i.e.,unrealistic or illo…
Knowledge-Guided Multi-Agent Framework for Application-Level Software Code Generation
Qian Xiong, Bo Yang, Weisong Sun +4
Automated code generation driven by Large Lan- guage Models (LLMs) has enhanced development efficiency, yet generating complex application-level software code remains challenging.…
UserTrace: User-Level Requirements Generation and Traceability Recovery from Software Project Repositories
Dongming Jin, Zhi Jin, Yiran Zhang +5
Software maintainability critically depends on high-quality requirements descriptions and explicit traceability between requirements and code. Although automated code summarization…
Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision
Xu Lu, Weisong Sun, Yiran Zhang +4
Automated code generation has long been considered the holy grail of software engineering. The emergence of Large Language Models (LLMs) has catalyzed a revolutionary breakthrough…