implementation detail · filed under post-training
Public and hidden verifier pairing
Pairs public verifiers that provide diagnostic feedback with hidden verifiers that evaluate held-out scenarios.
- 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.
Reward hacking is mitigated by isolating agents from verifiers, pairing public verifiers that offer diagnostic feedback with hidden verifiers that evaluate held-out scenarios, and applying penalty-based rewards under limited submission budgets.
usedunclearin Kimi K3Moonshot AI
Filed alongside
Other methods under post-training :: reward modelling.
Generative Reward ModelGroupwise Agentic GradingGroupwise Reward SynthesisAdversarial screeningLength-adjusted RL rewardVerifier cross-checkingAbstention-aware reward for factual QAAgentic Generative Reward ModelBehavior rubricsBinary task verifierBinary terminal-verifier rewardCollaboration bonusDeterministic chain of checkersDirect RL optimization of a generative reward modelFive-dimension comparative grading of passing patchesHack-agent screeningHybrid reward systemLanguage consistency rewardMonitoring-only penalty strategyMulti-level reward formulationMultiplicative reward synthesisNegative checks for unintended side effectsOutcome Reward ModelPer-token tool-error reward shaping