Tag
HKUST Assistant Professor Luo Yuyu released the open-source project Supervisor-Skills, which distills ten years of research experience into AI skills executable by large models, covering topic selection, writing, reviewing, etc., aiming to become an AI co-supervisor for researchers.
A new open-source tool automates the entire research paper refinement process, using Claude Code for execution and a separate model for evaluation to iteratively improve papers overnight. The system successfully upgraded a borderline rejected paper to submission-ready status through autonomous GPU experiments and narrative adjustments.