reinforce-ada-adaptive-sampling-rl-llms

【效率与协作】Recover learning signals in RL for LLM reasoning by dynamically allocating sampling budget based on prompt difficulty. Use log-objective weighting (1/p for pass rate p) to prioritize challenging examples, achieving 2x convergence speedup versus uniform sampling while maintaining identical compute budgets across math, coding, and general benchmarks.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准