New Paper: Adding RL After OPD Consistently Beats Pure OPD, Pure RLVR, and Joint Methods
gregd_nlp · x · 2026-09-16
A new paper examines the interplay between OPD and RLVR: don't skip RL after OPD. Adding an RL phase after OPD-based reasoning training consistently improves performance, and the OPD→RL pipeline outperforms pure OPD, pure RLVR, and many joint OPD+RL methods across reasoning tasks—offering empirical guidance on training order.
Related event: Paper: Sequential OPD-then-RL Training Beats Joint Optimization(4 posts)→
More from Research
- Tencent unveils Hyra 2.0, a research agent that builds reusable scientific tools — TencentHunyuan · 2026-11-02
- General Reasoning explains how to train agent swarms with RL and latency pressure — rosstaylor90 · 2026-11-02
- Mathematician Tony Feng: current-paradigm LLMs lack the diversity of thought research needs — littmath · 2026-11-02
- Measure Theory vs Probability: 'You're Confusing the Finger With the Moon' — LucaAmb · 2026-11-02
- DStill Distills Multi-Step Denoising Into One Pass, 6.45x Speedup for Diffusion Speculative Decoding — LucaAmb · 2026-11-02
- Radial gate objective cuts diffusion transformer FID from 16.24 to 11.83 — Junha Park · 2026-11-02