Fuli Luo on X: "Nearly half a year of silence. We spent it studying one problem: how far RL can scale. MiMo-V2.6 is in the middle of its RL run right now. Three things we scaled: compute (~2B tokens per step, 1568 prompts × 16 rollouts, fully async), environments and harnesses (multi-task agentic … / X

Post

Fuli Luo
@_LuoFuli
Nearly half a year of silence. We spent it studying one problem: how far RL can scale. MiMo-V2.6 is in the middle of its RL run right now. Three things we scaled: compute (~2B tokens per step, 1568 prompts × 16 rollouts, fully async), environments and harnesses (multi-task agentic RL, mixed across multiple harnesses in one run), and grader compute (agentic in-group credit assignment, with test-case and rubric-based rewards). We'll open-source the details piece by piece over the coming weeks. Streaming the run: mimo.xiaomi.com/rl/
6:52 PM · Sep 16, 2026
3.1M
Views
424
Fuli Luo
@_LuoFuli
Sep 16
We believe RL is one of the most scalable and efficient paths toward self-improvement.
12
Fuli Luo
@_LuoFuli
Sep 17
We hope this livestream sparks the research community’s interest in the core challenges of scaling RL and encourages researchers to help us refine our training recipe. We’ve been delighted to see so much insightful analysis based on the detailed training metrics.
5
Han Xiao
@hxiao
Sep 16
very nice and open! 🫡 just dont let cfo see this
GIF
4

Nearly half a year of silence. We spent it studying one problem: how far RL can scale. MiMo-V2.6 is in the middle of its RL run right now. Three things we scaled: compute (~2B tokens per step, 1568 prompts × 16 rollouts, fully async), environments and harnesses (multi-task agentic RL, mixed across multiple harnesses in one run), and grader compute (agentic in-group credit assignment, with test-case and rubric-based rewards). We'll open-source the details piece by piece over the coming weeks. Streaming the run: mimo.xiaomi.com/rl/

6:52 PM · Sep 16, 2026

3.1M

Views

424