PulseAugur
中
实时 10:27:17
English(EN) PathRouter: Aligning Rewards with Retrieval Quality in Agentic Graph Retrieval-Augmented Generation

PathRouter框架通过将奖励与检索质量对齐来改进代理图检索增强生成

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员推出了一种新颖的训练框架PathRouter，旨在增强代理图检索增强生成（GraphRAG）系统。该框架解决了仅基于结果的强化学习中固有的奖励别名和搜索-更新歧义等问题。PathRouter根据答案正确性和证据路径重叠来评估轨迹，区分不同类别以抑制捷径同时鼓励证据搜寻。实验表明，PathRouter在各种模型规模下显著提高了答案F1分数和证据路径重叠度。 AI

影响 PathRouter的方法可能带来更可靠、更准确的AI代理，它们能够更好地导航和利用复杂的信息网络。

排序理由 该集群包含一篇详细介绍AI模型新研究框架的学术论文。

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.CL TIER_1 English(EN) · Bo Wang, Heyan Huang, Yaolin Li, Wei Tang, Yuan Zhang, Wenbo Li, Mingze Gao, Ge Shi, Chong Feng ·

    PathRouter: Aligning Rewards with Retrieval Quality in Agentic Graph Retrieval-Augmented Generation

    arXiv:2606.16409v1 Announce Type: new Abstract: Agentic GraphRAG trains language-model agents to iteratively retrieve and reason over graph-structured evidence, enabling more accurate and context-aware decision-making by efficiently navigating complex information networks. Howeve…

  2. arXiv cs.CL TIER_1 English(EN) · Chong Feng ·

    PathRouter: Aligning Rewards with Retrieval Quality in Agentic Graph Retrieval-Augmented Generation

    Agentic GraphRAG trains language-model agents to iteratively retrieve and reason over graph-structured evidence, enabling more accurate and context-aware decision-making by efficiently navigating complex information networks. However, outcome-only reinforcement learning suffers f…

相关实体

相关话题