Model techniques map
Techniquespost-trainingrollout & RL infrastructure

specific method · filed under post-training

Co-located long-context agentic RL system

Combines partial rollouts, external KV-cache retention, adaptive throttling, and resumable microVM sandboxes to preserve long-lived state.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

our co-located system combines partial rollouts, external KV-cache retention, adaptive throttling and resumable microVM sandboxes to preserve long-lived model and environment state.

usedsoftware implementationin Kimi K3Moonshot AI

Filed alongside

Other methods under post-training :: rollout & RL infrastructure.