Open Models Almanac
Methodspost-trainingreinforcement learning algorithm

specific method · filed under post-training

Mixed-domain reinforcement learning

Mixed-domain reinforcement learning trains a model with GRPO across reasoning, agent, and human alignment data in a single RL stage.1 It balances performance across diverse domains while avoiding the catastrophic forgetting of multi-stage training.2

How this definition was written

Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.

  1. we merge reasoning, agent, and human alignment training into one RL stage — DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
  2. effectively balances performance across diverse domains while circumventing the catastrophic forgetting issues commonly associated with multi-stage training paradigms — DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Also called Mixed reinforcement learning, Mixed multi-domain reinforcement learning, mixed RL, Mixed RL Training.

sources
5
models
2
labs adopt it
2
strongest
core

Documented in

Liquid AI

Evidence

5 quotes from 5 sources, one card per model, each opening with its strongest.

How sources treat it
used 3core 2

LFM3-1.7B

Liquid AIadopted3 sources

Post-training from this checkpoint (SFT, mixed RL, multi-domain on-policy distillation, and agentic RL) produces LFM3-1.7B.

usedpost trainingin LFM3-1.7BLiquid AI
2 more from this model

Mixed reinforcement learning: many domains trained at once, from math and code to SQL and structured outputs.

usedpost trainingin LFM3-1.7BLiquid AI

many domains trained at once, from math and code to SQL and structured outputs

usedpost trainingin LFM3-1.7BLiquid AI
↑