---
id: "lib-2026-10-08-mimo-v2-6-scaling-reinforcement-learning-towards"
type: "library"
title: "MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement"
lang: "EN"
org: "Xiaomi LLM-Core 小米 MiMo"
source_type: "Paper"
date: "2026-10-08"
week: "2026-W41"
url: "https://nosov.ai/library/lib-2026-10-08-mimo-v2-6-scaling-reinforcement-learning-towards/"
original_url: "https://arxiv.org/pdf/2610.11959"
tags: ["lane a", "ai technology", "training cost"]
---

# MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement

## English summary

Rare cost disclosure: RL post-training ~USD 2.6M (Pro, 1.02T/42B active) and about 0.9M (Flash); per step 1,568 prompts x16 rollouts, 2.7-3.7B tokens; rollout 43.8% vs training 43.5% of compute; 68% of RL batch is code tasks. Lab self-report kept for cost data. Found via InfoQ gNdWoDM8ygkAjXfsLaBK.

Original: https://arxiv.org/pdf/2610.11959