Model techniques map
Techniquespost-trainingagentic post-training

specific method · filed under post-training

Autonomous Execution Tasks (AET)

An environment paradigm for long-horizon agent training using tool-based actions, execution budgets, and independent verification.

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.

We introduce Autonomous Execution Tasks (AET), an environment paradigm that trains long-horizon agent intelligence through verify-in-the-loop optimization. Each task specifies an initial state, a constrained goal, a tool-based action space, execution budgets, and an independent verifier.

usedunclearin Kimi K3Moonshot AI

Filed alongside

Other methods under post-training :: agentic post-training.