Reproduce “SkillBuffBench: Measuring What Agent Skills Contribute across Harnesses, Models, Skill Access Modes and Memory” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Gengyue Dong, Ye Wei, Zheng Zhu, Yidong Han, Jiale Miao, Xiaojun Jia, Guanghui Li
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.