Reproduce “One Task, Many Interfaces: Simple Cross-Interface Consistency Training Improves LLM Agent Robustness” 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

Artin Tajdini, Manpreet Kaur, Peng Qi

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