# TAP-RAG: Task-Aware Policy Control for Long-Document Multimodal Question Answering

Source: [TAP-RAG: Task-Aware Policy Control for Long-Document Multimodal Question Answering](<https://www.sota2.com/research/paper/6a604e8def5cfba72b497970>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-23T05:00:05.031Z

Authors: Zhong Ji, Keqi Jin, Yan Zhang, Jiasheng Li

Published: 2026-07-21T09:59:13.000Z

## Abstract

Long-document multimodal question answering requires more than retrieving relevant chunks from a large document. Different queries require different evidence behavior. Existing multimodal RAG systems improve evidence access through text chunks, page images, graph links, or heterogeneous document elements, but they often apply a largely query-agnostic evidence-use strategy. We present TAP-RAG, a task-aware policy-controlled RAG framework for long-document multimodal QA. TAP-RAG contains a main controller, the Task-Aware Policy Controller (TAPC), and two policy-guided evidence executors: Task-Aware Query-Guided Flow Diffusion (TA-QFD) and Task-Aware Visual Enhancement (TAVE). For each query, TAPC predicts the task prior, estimates visual/local/global evidence signals, and produces an executable policy. TA-QFD then expands textual and structural evidence over the multimodal document graph, while TAVE selectively inspects page images when visual or layout evidence is needed. A guarded synthesis stage fuses text, visual, and structural evidence and abstains when support is insufficient. On DocBench and MMLongBench-Doc, TAP-RAG achieves the best overall accuracy among the compared systems, improving over a matched multimodal-RAG baseline by +9.1 points (61.1 to 70.2) and +4.5 points (42.2 to 46.7), respectively.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2607.18917>)

[PDF](<https://arxiv.org/pdf/2607.18917.pdf>)