chaining-evidence-rl

【效率与协作】Train search agents using citation-aware rubric rewards that decompose complex questions into verifiable single-hop facts. Agents learn to chain evidence through explicit source citations, preventing hallucinations and shortcut exploitation. Citation-aware Group Relative Policy Optimization (C-GRPO) combines rubric and outcome rewards, enabling agent…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准