Reproduce “Crucible: Quantifying the Potential of Control Algorithms through LLM Agents” 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

Lianchen Jia, Chaoyang Li, Qian Houde, Tianchi Huang, Jiangchuan Liu, Lifeng Sun

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.