smart-search-query-refinement

【效率与协作】Improve LLM search agents by optimizing query quality at each step using process-level rewards. Framework teaches agents to iteratively refine search queries through imitation, alignment, and generalization stages. Agents learn to identify low-quality queries and regenerate improved ones, significantly improving search efficiency and answer quality o…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准