RAG / 检索增强生成

GRAIL:Learning to Interact with Large Knowledge Graphs for Retrieval Augmented Reasoning

GRAIL:学习与大规模知识图谱交互以实现检索增强推理

Ge Chang, Jinbo Su, Jiacheng Liu, Pengfei Yang, Yuhao Shang, Huiwen Zheng, Hongli Ma, Yan Liang, Yuanchun Li, Yunxin Liu

专题命中 图谱与结构化RAG ：RAG(abstract,abstract_cn)；retrieval-augmented generation(abstract)；分类 cs.AI

AI总结 GRAIL通过结合LLM引导的随机探索与路径过滤，建立数据合成管道，学习动态决策策略，提升知识图谱检索的精度与简洁性平衡，实验表明在三个知识图谱问答数据集上准确率和F1值分别提升21.01%和22.43%。

Comments This is a duplicate submission of the article "Enhancing Agentic Textual Graph Retrieval with Synthetic Stepwise Supervision" [arXiv:2510.03323]. The content is identical to the newer version. This entry is being withdrawn to avoid redundancy