Ziyang Huang

MS→incoming PhD @JHUCompSci @jhuclsp

[Ziyang Huang @zyh_ai]

We evaluated multiple agent setups, including an orchestrated multi-phase agent and off-the-shelf CLI agents, across frontier models.

The headline: scientific reproduction remains hard for today's coding agents.

Check it out here:
🌐 https://t.co/60J04wXySd

[Ziyang Huang @zyh_ai]

Can coding agents actually reproduce scientific findings — not just write code, but rerun the science?

We built AutoMat to find out. 🧪🤖

AutoMat is a benchmark of 85 expert-curated reproduction tasks from computational materials science.