Reproduce “Generative Grading: Near Human-level Accuracy for Automated Feedback on Richly Structured Problems” 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
Ali Malik, Mike Wu, Vrinda Vasavada, Jinpeng Song, Madison Coots, John Mitchell, Noah Goodman, Chris Piech
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.