Tag
An arXiv paper presenting K-Dense BYOK, a free open-source AI research assistant that runs locally on the researcher's own machine (bring-your-own-keys) and records every agent action in an immutable, hash-chained Living Lab Notebook and provenance log to combat model overclaiming. On twenty interdisciplinary prompts scored against a pre-fixed rubric, it outperformed two managed platforms (Claude Science, Biomni Lab) on both scientific quality and research execution.
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.