Mapa del conocimiento

Reinforcement Learning With Verifiable Rewards

1 paper toca esta idea.

Papers

Teaching an AI to grade its own reasoning with a checklist beats giving it one right answer

Conceptos relacionados

Ideas que aparecen junto a Reinforcement Learning With Verifiable Rewards.

Chain-Of-Thought Credit Assignment Knowledge Distillation Reasoning Language Models Rubric-Conditioned Self-Distillation Science Reasoning Benchmarks Self-Distillation