Reproduce “Low-code LLM: Graphical User Interface over Large Language Models” 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
Yuzhe Cai, Shaoguang Mao, Wenshan Wu, Zehua Wang, Yaobo Liang, Tao Ge, Chenfei Wu, Wang You and 5 more
Low-code LLM lets users shape an LLM response by reviewing and editing a visible workflow drafted from a task prompt. A Planning LLM creates named, described steps, which users can revise before an Executing LLM responds; workflows may include conditional jumps. Four qualitative GPT-3.5-turbo pilot cases illustrate the approach, but do not establish general improvements in quality, reliability, or efficiency.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.