2 papers
cs.SE2026
SGCR: A Specification-Grounded Framework for Trustworthy LLM Code Review
Kai Wang, Bingcheng Mao, Shuai Jia +4
Automating code review with Large Language Models (LLMs) shows immense promise, yet practical adoption is hampered by their lack of reliability, context-awareness, and control. To…
cs.SE2026
ArchAgent: Scalable Legacy Software Architecture Recovery with LLMs
Rusheng Pan, Bingcheng Mao, Tianyi Ma +1
Recovering accurate architecture from large-scale legacy software is hindered by architectural drift, missing relations, and the limited context of Large Language Models (LLMs). We…