Chaining Evidence Rl

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 agents to solve multi-hop reasoning tasks with high factual grounding and transparency.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 8972397996

Frequently asked questions

npx get-skill add adu2021/chaining-evidence-rl