AI Agents Outperform Top Human Reviewers On Nature Family Papers

Recently, there's been complaints on low-quality AI reviews at conferences and journals. What if we put the frontier LMs into an agent harness? With the right setup, on 82 Nature-family papers, 45 expert scientists judged that AI reviewers outperform the best human reviewer! 🤗 https://huggingface.co/papers/2605.20668