New paper: OPD→RL beats pure OPD, pure RLVR, and joint OPD+RL methods
zhaoran_wang · x · 2026-09-17
A new paper from xiyenlp on the interplay between OPD and RLVR:
- After using OPD for reasoning, adding an RL phase consistently improves performance
- Across reasoning tasks, the OPD→RL pipeline outperforms pure OPD, pure RLVR, and many joint OPD+RL methods
- Takeaway: don't skip RL after OPD
Retweeted by zhaoranwang as "a real important work."
Related event: Paper: Sequential OPD-then-RL Training Beats Joint Optimization(4 posts)→
More from Research
- Detecting covert instruction-following via internal representations parallels J-space work — dioscuri · 2026-11-02
- Xiaomi MiMo's CodeSpecWeave trains coding agents on interdependent specs for long-horizon coding — XiaomiMiMo · 2026-11-02
- Mistral Large 4 writes a quantum chemistry SCF solver from scratch with one short prompt — MistralAI · 2026-11-02
- Hunting for the most concrete "curing cancer with AI" roadmap of 2025 — iskander · 2026-11-02
- New theory paper proves linear decay is the unique minimax-optimal stepsize schedule for SGD — konstmish · 2026-11-02
- Karpathy's nanochat: the best ChatGPT $100 can buy, near 60k GitHub stars — karpathy · 2026-11-02