MiMo-V2.6 RL framework
Named by 2 kept items in this workspace.
Search every workspace for MiMo-V2.6 RL framework. It matches the name as written, so it can find other things that share it.
The items that name it 2
Open-sourced infrastructure for mixed-task agentic RL, with a unified trajectory representation, high-concurrency multi-framework rollout, decoupled control and data planes, and training-inference consistency
Open-sourced RL framework for mixed-task agentic RL: unified trajectory representation, high-concurrency multi-framework rollout, decoupled control and data planes, and training-inference consistency.
All technologies in this workspace.