Edward Hu(@edwardjhu):How does one RL post-train a 397B model for long-horizon knowledge work? 👩‍💼 We share every step we took to bring Qwen 3.5 397B from 16.1% Pass@1 to 27.3% on APEX-Agents using DPPO, including final models weights and the full training script🚀 This is the first of many works from Mercor Research on open model training research. Full blog: https://t.co/GWgR2DB7iy Source code:

Edward Hu

@edwardjhu

Head of AI Modeling @ Mercor Ph.D. with Yoshua Bengio | ex-OpenAI

加入 December 2019

42 正在关注 9.3K 粉丝

Edward Hu@edwardjhu

2026.09.01 21:19

How does one RL post-train a 397B model for long-horizon knowledge work? 👩‍💼 We share every step we took to bring Qwen 3.5 397B from 16.1% Pass@1 to 27.3% on APEX-Agents using DPPO, including final models weights and the full training script🚀 This is the first of many works from Mercor Research on open model training research. Full blog: Source code:

显示更多