Model techniques map
Techniques

general family · not yet filed

Scalable reinforcement learning across million-agent environments

source
1
model
1
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

core 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

Reinforcement learning scaled across million-agent environments with progressively complex task distributions for robust real-world adaptability.

corepost trainingin Qwen3.5-122B-A10BQwen