Large language models (LLMs) are increasingly used for code generation, yet generated programs may exhibit social bias through unfair or differential treatment of sensitive demographic attributes. While prior work mainly studies direct code generation, bias in reasoning-based generation remains underexplored. We conduc...
Wei-Feng Sun, Jie-Ke Shi, Zhou Yang et al.· 0 citations
FailFast-RestartSmart, a two-stage controller for a single active trajectory that supports early termination with sequential same-policy recovery, and results support early termination with sequential same-policy recovery.
Chenyu Wang, Yunbo Lyu, Junda He et al.· 1 citation
Results show that behavior interpretation and project-aware context retrieval both contribute substantially to generation quality, and demonstrate that LLMs can effectively connect natural-language behavior specifications with project code and support specification-driven software development.
This paper identifies patch verbosity as a major yet overlooked concern in LLM-based APR and proposes RECAP, a lightweight, plug-and-play adapter that attaches to existing repair frameworks after generation that achieves a substantially better size-correctness tradeoff.
Wen-Qiang Luo, J. Keung, Xiaoyu Shi et al.· 0 citations
This paper is the first to study how SE processes are changing in the development of SE agents and what challenges developers face, and describes a seven-stage workflow and five process shifts, including a move toward evaluation-driven development.
Yunbo Lyu, David Williams, Jieke Shi et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
