RouteDRAG：学习面向多模态文档 RAG 的智能体执行路由与控制

arXiv cs.AI 论文
rag multimodal agentic-retrieval document-understanding reinforcement-learning

摘要

RouteDRAG 是一个基于学习的框架，用于在多模态文档检索增强生成（RAG）中决定是否调用智能体及其执行路径。在两个基准测试中，相比仅使用短路径执行，平均提升了 3.47 个百分点，且仅将 79.3% 的查询分配给智能体。

arXiv:2610.36444v1 Announce Type: new Abstract: Web-based applications increasingly rely on understanding long multimodal documents, where answering questions often requires combining information across pages, tables, and figures. Agentic retrieval-augmented generation addresses these tasks through iterative retrieval and reasoning. However, Agentic execution is not always necessary, introducing additional computation and potentially incorrect answers. Our empirical analysis reveals that Agentic execution provides query-dependent benefits, while additional operations may improve, preserve, or degrade answer accuracy. These findings motivate controlling both Agent invocation and subsequent execution. To address these challenges, we propose RouteDRAG, a learning-based framework comprising four components. Unified Document Index organizes multimodal content into a graph-backed index and derives query representations from initial retrieval. Adaptive Path Routing preserves exact answering and predicts the relative benefit of Agent over shorter execution paths. Dynamic Agent Execution maintains an evolving workspace and refines Planner proposals to control tool use and termination. Sequential Policy Learning first trains operation control from observed outcomes and then trains path routing using the resulting Agent's performance. Across two benchmarks, RouteDRAG achieves an average accuracy improvement of 3.47 percentage points over shorter-path-only execution while assigning only 79.3% of queries to Agent. Notably, it also surpasses uniform Agent execution on both benchmarks while requiring fewer answering calls. Our code is now available at https://github.com/Ereshkigal1/RouteDRAG.
查看原文
查看缓存全文

缓存时间: 2026/10/28 07:55 

# RouteDRAG: Learning to Route and Control Agentic Execution for Multimodal Document RAG
Source: [https://arxiv.org/abs/2610.36444](https://arxiv.org/abs/2610.36444)
[View PDF](https://arxiv.org/pdf/2610.36444)[HTML \(experimental\)](https://arxiv.org/html/2610.36444v1)

> Abstract:Web\-based applications increasingly rely on understanding long multimodal documents, where answering questions often requires combining information across pages, tables, and figures\. Agentic retrieval\-augmented generation addresses these tasks through iterative retrieval and reasoning\. However, Agentic execution is not always necessary, introducing additional computation and potentially incorrect answers\. Our empirical analysis reveals that Agentic execution provides query\-dependent benefits, while additional operations may improve, preserve, or degrade answer accuracy\. These findings motivate controlling both Agent invocation and subsequent execution\. To address these challenges, we propose RouteDRAG, a learning\-based framework comprising four components\. Unified Document Index organizes multimodal content into a graph\-backed index and derives query representations from initial retrieval\. Adaptive Path Routing preserves exact answering and predicts the relative benefit of Agent over shorter execution paths\. Dynamic Agent Execution maintains an evolving workspace and refines Planner proposals to control tool use and termination\. Sequential Policy Learning first trains operation control from observed outcomes and then trains path routing using the resulting Agent's performance\. Across two benchmarks, RouteDRAG achieves an average accuracy improvement of 3\.47 percentage points over shorter\-path\-only execution while assigning only 79\.3% of queries to Agent\. Notably, it also surpasses uniform Agent execution on both benchmarks while requiring fewer answering calls\. Our code is now available at[this https URL](https://github.com/Ereshkigal1/RouteDRAG)\.

## Submission history

From: Rui Qian \[[view email](https://arxiv.org/show-email/0144bc5f/2610.36444)\] **\[v1\]**Tue, 27 Oct 2026 00:45:49 UTC \(1,222 KB\)

相似文章

@ando_w: https://x.com/ando_w/status/2075468963098546520

X AI KOLs Timeline

本文介绍如何将单轮RAG升级为Agentic RAG，通过让LLM自主决定多次检索和调用工具，解决复合问题的多步推理。提供了基于Qwen3.7-Max的代码示例和实现思路。

@Jerry_fsy: 如果你正在做 Agent，或者准备 Agent 相关岗位的面试，RAG 和记忆系统都是绕不开的知识点。很多人觉得 RAG 已经落后了，没有人使用了，但实际上，它是一种上下文管理策略，在很多现实的业务中，会将Agent与RAG结合，从而满足…

X AI KOLs Timeline

作者分享了一份面向 Agent 开发与面试的 RAG 与记忆系统学习路线，覆盖分块、混合检索、Rerank、向量数据库选型以及短期/长期记忆管理，并附上 Lewis 等人的 RAG 原始论文等参考资料。