Recursive Reward Improvement via Adversarial Meta-Prompt Evolution
Recursive Self-Improvement (RSI) has gained wide attention for its ability to work with limited data. In a proposer-solver loop, a proposer model writes training tasks and a solver model learns to solve them through reinforcement learning. Such loops have succeeded in mathematics and coding, where every answer can be c...
Wei Dai, Qian-Chu Liu, Guang-Hui Qin et al.
· 1 citation