Reproduce “Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks” 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

Neeraj Karamchandani, Piyush Nagasubramaniam, Xinhong Xie, Sencun Zhu, Dinghao Wu

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