Alistair Letcher

Rubric Curriculum RL: Exploiting the Generation-Verification Gap in Non-Verifiable Domains

Reinforcement learning with verifiable rewards (RLVR) has led to significant gains in math and code generation. Extending these gains to open-ended domains remains challenging: ground-truth verification is unavailable, human annotation is expensive, and learned reward models are prone to reward hacking. The generation-...