Open Models Almanac
Methodspost-trainingrollout & RL infrastructure

specific method · filed under post-training

Asynchronous RL framework for large-scale agent scaffolds and environment orchestration

Describes asynchronous RL frameworks for orchestrating large-scale agent scaffolds and environments, without specifying a distinct internal mechanism.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See rollout & RL infrastructure for the methods filed beside it.

sources
3
model
1
lab adopt it
1
strongest
used

Documented in

Alibaba (Qwen)

Evidence

3 quotes from 3 sources, one card per model, each opening with its strongest.

How sources treat it
used 3

Qwen3.5-397B-A17B

Alibaba (Qwen)adopted3 sources

asynchronous RL frameworks supporting massive-scale agent scaffolds and environment orchestration.

usedpost trainingin Qwen3.5-35B-A3BQwen Team
2 more from this model

asynchronous RL frameworks supporting massive-scale agent scaffolds and environment orchestration

usedsoftware implementationin Qwen3.5-122B-A10BQwen Team

asynchronous RL frameworks supporting massive-scale agent scaffolds and environment orchestration

usedpost trainingin Qwen3.5-397B-A17BQwen Team
↑