composition-rl-prompts

【效率与协作】Convert easy, high-accuracy training prompts into harder compositional problems by sequentially chaining multiple prompts together. Use Composition-RL to maintain effective learning signals during RL training when many prompts achieve near-perfect accuracy, enabling curriculum learning through progressive compositional depths.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准