Reproduce “Executable Human Study Programs with Silicon Participants” 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
Xuan Liu, Haoyang Shang, Yuanjun Feng, Shao-Yu Chu, Qiyu Li, Yash Raj Shrestha, Haojian Jin
HumanStudyProgram turns a published study’s procedure into a reusable program, separating its rules and sequence from the participants who run it. Researchers review an extracted description, then use Show and Ask operations with ordinary Python to configure and inspect runs with language-model agents. In a 12-researcher review, all completed the workflow; this supports protocol inspection, not claims about human behavior.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.