---
type: "post"
id: "reflection-publishes-beam-customization-recipes-self-distillation-distillation-5a2a4b"
slug: "reflection-publishes-beam-customization-recipes-self-distillation-distillation-5a2a4b"
title: "Reflection publishes Beam customization recipes: self-distillation, distillation to Gemma 4 E4B and RL with Miles, NeMo RL and SkyRL"
description: "Reflection has published a Beam customization overview with end-to-end recipes for adapting the open-weight Beam model."
retrieval_nugget: "Reflection has published a Beam customization overview with end-to-end recipes for adapting the open-weight Beam model."
published_at: "2026-10-24"
updated_at: "2026-10-24"
record_date: "2026-10-24"
date_kind: "published_at"
topics: ["models","open-models"]
entities: ["Reflection","Beam","Gemma 4 E4B","Miles","NeMo RL","SkyRL","Triton","DAPO-Math-17K"]
related_patterns: []
novelty_label: "same_event"
what_changed: "Same event as Reflection AI open-sources Beam’s weights, post-training recipes"
prior_refs: ["memory:6a3e86ad-5269-8cce-a9ac-dcb959a4730e"]
source_url: "https://developers.reflection.ai/customization-overview"
source_urls: ["https://developers.reflection.ai/customization-overview"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:reflection-publishes-beam-customization-recipes-self-distillation-distillation-5a2a4b"
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/reflection-publishes-beam-customization-recipes-self-distillation-distillation-5a2a4b/","markdown":"https://newruntime.com/posts/reflection-publishes-beam-customization-recipes-self-distillation-distillation-5a2a4b.md","json":"https://newruntime.com/posts/reflection-publishes-beam-customization-recipes-self-distillation-distillation-5a2a4b.json"}
---

# Reflection publishes Beam customization recipes: self-distillation, distillation to Gemma 4 E4B and RL with Miles, NeMo RL and SkyRL

## Retrieval answer

Reflection has published a Beam customization overview with end-to-end recipes for adapting the open-weight Beam model.

Reflection has published a Beam customization overview with end-to-end recipes for adapting the open-weight Beam model. The developer documentation says each recipe includes the configurations and scripts used by Reflection, hardware and runtime records, and, where training targets quality, before-and-after measurements made with the same evaluation method.

The listed work includes Beam self-distillation on verified Triton kernels; SWE-agent and tool-calling-reasoning distillation into Gemma 4 E4B; and GRPO reinforcement learning on DAPO-Math-17K through Miles, NeMo RL, and SkyRL. The page says one data-synthesis recipe has Beam generate tool-calling thoughts for 3,941 public conversations. Another creates software-engineering environments with hidden tests, retains only passing trajectories, and uses them for training data.

Reflection also gives sizing guidance for Beam-1.0-501B-A23B, described as 501B total parameters with 23B active. It lists one 8x H200 node for QLoRA, three to eight nodes for full fine-tuning, and four to eight for RL post-training. The page does not establish that these recipes will reproduce the reported results on other tasks, datasets, hardware, or deployments.

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: [Models](https://newruntime.com/topics/models.md): Explore the models topic hub.
- topic hub: [Open Models](https://newruntime.com/topics/open-models.md): Explore the open-models 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)