specific method · filed under post-training
Agentic Generative Reward Model
An agentic generative reward model for non-verifiable tasks that retains tournament-style group rewards based on binary comparisons.
Also called Agentic Generative Reward Model (GRM).
- 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.
For non-verifiable general tasks, we adopt an Agentic Generative Reward Model (GRM), retaining the tournament-style group reward with binary comparisons as in Kimi K2.5
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 QABehavior 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 shapingPrinciple-conditioned Generative Reward Model