James Zou

Paper2Agent automatically converts research papers into interactive AI agents capable of reproducing original results and executing novel scientific queries, including discovering new genetic variants associated with ADHD.

“Co-author of the Paper2Agent research paper introducing the framework that converts research papers into AI agents”

“Co-author of Stanford study on the shelf life of LLM findings and claim persistence.”

“Stanford researcher building methods for automating research with LLMs and specialized tools; notes limitations in automating real-world experiments.”

TTT-Discover enables large language models to perform reinforcement learning at test time, adapting to problem-specific tasks and achieving state-of-the-art results in mathematics, GPU kernels, algorithms, and biology.

“Co-authored TTT-Discover reinforcement learning system for test-time LLM training.”