---
type: "post"
id: "ifm-open-sourced-rl360-the-rl-infrastructure-behind-4e4318"
slug: "ifm-open-sourced-rl360-the-rl-infrastructure-behind-4e4318"
title: "IFM open-sourced RL360 , the RL infrastructure behind K2 Horizon's six domain experts, under Apache 2.0."
description: "The Institute of Foundation Models (IFM) at MBZUAI has open-sourced RL360, a reinforcement-learning post-training codebase used for the K2 Horizon model family."
retrieval_nugget: "The Institute of Foundation Models (IFM) at MBZUAI has open-sourced RL360, a reinforcement-learning post-training codebase used for the K2 Horizon model family."
published_at: "2026-10-22"
updated_at: "2026-10-22"
record_date: "2026-10-22"
date_kind: "published_at"
topics: ["harness-engineering","agent-runtime"]
entities: ["Institute of Foundation Models","MBZUAI","RL360","K2 Horizon","Merge360"]
related_patterns: ["harness-architecture-outlives-model-choice"]
novelty_label: "new_fact"
what_changed: "IFM has now open-sourced RL360, the reinforcement-learning infrastructure used behind K2 Horizon’s six domain experts, under Apache 2.0."
prior_refs: ["memory:8cd2eaa4-52c8-8ea3-a199-095f7a0582fd"]
source_url: "https://github.com/ifm-ai/RL360"
source_urls: ["https://github.com/ifm-ai/RL360"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:ifm-open-sourced-rl360-the-rl-infrastructure-behind-4e4318"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/ifm-open-sourced-rl360-the-rl-infrastructure-behind-4e4318/","markdown":"https://newruntime.com/posts/ifm-open-sourced-rl360-the-rl-infrastructure-behind-4e4318.md","json":"https://newruntime.com/posts/ifm-open-sourced-rl360-the-rl-infrastructure-behind-4e4318.json"}
---

# IFM open-sourced RL360 , the RL infrastructure behind K2 Horizon's six domain experts, under Apache 2.0.

## Retrieval answer

The Institute of Foundation Models (IFM) at MBZUAI has open-sourced RL360, a reinforcement-learning post-training codebase used for the K2 Horizon model family.

The Institute of Foundation Models (IFM) at MBZUAI has open-sourced RL360, a reinforcement-learning post-training codebase used for the K2 Horizon model family. The GitHub repository is licensed under Apache 2.0.

The release includes source code, recipes, Docker material and components for the training infrastructure. Its repository history also documents Merge360, tooling for checkpoint merging, with methods including linear soup, task arithmetic, TIES, RAM/RAM+, ULP-gate, Gram-soup and ISO. A supplied recipe downloads a K2 Horizon 375B-A23B base model and five RL experts, then runs the documented merge settings.

IFM describes RL360 as the infrastructure behind K2 Horizon's six domain experts. The repository provides code and configuration rather than a hosted service or a newly released model. It does not establish the compute cost of training, the hardware required, independent reproduction of K2 Horizon results, or performance when the stack is applied to other models.

Public source: https://github.com/ifm-ai/RL360

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Harness Engineering](https://newruntime.com/topics/harness-engineering.md): Explore the harness-engineering topic hub.
- topic hub: [Agent Runtime](https://newruntime.com/topics/agent-runtime.md): Explore the agent-runtime topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)