Model techniques map
Techniquespost-trainingreward modelling

specific method · filed under post-training

Adversarial screening

Uses adversarial probing during reinforcement learning to expose reward-hacking weaknesses; the evidence does not establish a more specific screening procedure.

sources
2
models
2
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 2

Documented in

Evidence

2 spans quoted from the sources, strongest treatment first.

Throughout RL, environment hardening, adversarial screening, and verifier cross-checks keep the loop honest against reward hacking.

usedpost trainingin MiMo-V2.6-Pro-RLXiaomi

Throughout RL, environment hardening, adversarial screening, and verifier cross-checks keep the loop honest against reward hacking.

usedpost trainingin MiMo-V2.6-Flash-RLXiaomi

Filed alongside

Other methods under post-training :: reward modelling.