← all releases
Institute of Foundation Models (IFM) at MBZUAI·Oct 22, 2026·v0.1.0·open source

RL360

RL360 is an open-source reinforcement learning infrastructure designed for the post-training of language models, specifically powering the K2 Horizon model family. It enables training models on complex tasks involving coding, tool use, and interaction with sandboxed environments through a distributed Ray-based architecture.

Reinforcement LearningLLM Post-trainingAgentic AIOpen Source
overview

RL360 is an open-source reinforcement learning infrastructure designed for the post-training of language models, specifically powering the K2 Horizon model family. It enables training models on complex tasks involving coding, tool use, and interaction with sandboxed environments through a distributed Ray-based architecture.

key features
  • 01Distributed reinforcement learning orchestration using Ray
  • 02Support for sandboxed agent execution and tool-use verification
  • 03Integration with Megatron-LM and SGLang for scalable training and inference
  • 04Advanced weight merging techniques for RL expert checkpoints
  • 05Configurable Slurm-based training recipes for coding and agentic tasks
related productsbrowse all →
MiroThinkeropen sourceMiroThinker is an open-source search agent model developed by MiroMindAI, designed for tool-augmented reasoning and real-world information seeking. It aims to match the deep research capabilities of leading AI models like OpenAI's Deep Research and Google's Gemini Deep Research.Letta Code SDKopen sourceThe Letta Code SDK is a software development kit that enables developers to build deeply personalized agents with persistent memory that learn over time. It serves as the interface to Letta Code, facilitating the creation of stateful agents capable of continuous learning and improvement.OB-1open sourceOB-1 is a self-improving coding agent developed by OpenBlock Labs, designed to autonomously handle the full development lifecycle, from project management to pull requests. It integrates seamlessly into existing workflows, enhancing productivity and code quality.