FLOWREADER: Min-Cost Flow Optimization for Multi-Modal Long Document Q&A

• URL: http://arxiv.org/abs/2606.07235v2
• Date: Mon, 08 Jun 2026 12:31:09 GMT
• Title: FLOWREADER: Min-Cost Flow Optimization for Multi-Modal Long Document Q&A
• Abstract summary: We introduce FLOWREADER, which reframes evidence assembly as a min-cost flow problem on a multimodal node graph.<n>The optimal flow is decomposed into candidate evidence paths, a compact non-redundant subset is selected by entropy-regularized replicator dynamics.<n>FLOWREADER is best on the two subsets dominated by fragmented evidence PaperTab and SlideVQA.
• Score: 6.071121358322323
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long, multimodal documents force retrieval-augmented systems to assemble answers from evidence fragmented across text, tables, and slides broken across cells in a long table, spread over multiple slides, or split between a figure and its discussion. Top-$k$ chunk retrieval treats each fragment independently and cannot represent how evidence connects. We introduce FLOWREADER, which reframes evidence assembly as a min-cost flow problem on a multimodal node graph: a single scoring vector $h$ controls source selection (via MMR), sink selection (via a length-aware answerability proxy), and the costs and capacities of every edge. The optimal flow is decomposed into candidate evidence paths, a compact non-redundant subset is selected by entropy-regularized replicator dynamics, and parallel VLM workers under a dual-process gate produce the answer with a single System-2 refinement pass triggered when answer consistency is low or the routed flow is strained. On VisDoMBench, FLOWREADER is best on the two subsets dominated by fragmented evidence PaperTab ($58.40$, $+1.30$ over G^{2}-Reader) and SlideVQA ($72.93$, $+0.62$) and competitive on SPIQA, FetaTab, and SciGraphQA. Macro-averaged across all five subsets, FLOWREADER ($65.47$) is within $0.74$ of the strongest baseline (G^{2}-Reader, $66.21$). Overall, these results show that min-cost flow performs well on fragmented multimodal evidence, where top-$k$ retrieval fails. It also provides a unified way to control scoring, routing, selection, and adaptive compute together.

Related papers

• Stable Curves, Unstable Items: Item-Level Scaling Heterogeneity in Video LLMs [16.31176289941024]
  We show that Video LLMs improve smoothly or saturate as visual budgets grow.<n>We represent each frozen model--item pair by its response trajectory under controlled visual budgets.<n>We derive matched-grid measures of configuration complementarity, harmful transitions, and text overwrite.
  arXiv  Detail & Related papers  (2026-08-07T09:25:20Z)
• Modality Relevance is not Modality Utility: Post-hoc Selective Modality Escalation for Cost-Aware Multimodal RAG [7.082282444371973]
  We show that the relevance of a modality to a question is a weak predictor of whether that modality is actually needed to answer correctly.<n>We propose textbfpost-hoc selective modality escalation: answer cheaply from text and tables, run a verifier, and pay for VLM evidence only there.
  arXiv  Detail & Related papers  (2026-07-03T15:28:16Z)
• Rethinking RAG in Long Videos: What to Retrieve and How to Use It? [56.38819694781005]
  We introduce V-RAGBench, a benchmark of $langle$query, evidence chunk, answer$rangle$ triplets that enables faithful, decoupled evaluation of retrieval and generation.<n>We also present CARVE, a method that runs parallel retrievers across configurations and employs chunk-adaptive reranking to identify the winning configuration for each chunk.
  arXiv  Detail & Related papers  (2026-06-11T10:05:49Z)
• FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse [58.80348559239392]
  Large Language Model (LLM)-based multi-agent systems are increasingly powerful.<n>Task-level methods spend substantial offline compute yet deploy only a single workflow.<n> query-level methods synthesize a new workflow per query at substantial cost.<n>We present FlowBank, a framework for portfolio-based agentic workflow optimization.
  arXiv  Detail & Related papers  (2026-06-09T17:58:21Z)
• Constrained Dominant Sets for Multimodal Document Question Answering [3.7607300100158345]
  Long multimodal document question answering is limited by which evidence reaches the reader, rather than by the quantity retrieved.<n>This work introduces a retriever that selects evidence as a Constrained Dominant Set on a query-augmented affinity graph.
  arXiv  Detail & Related papers  (2026-06-05T13:24:46Z)
• GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs [3.9266376632068485]
  GridProbe is an efficient training-free posterior-probing inference paradigm.<n>It scores evidence in answer space using a frozen VLM's own reasoning.<n>It selects question-relevant frames adaptively, resulting in sub-quadratic attention cost with little to no accuracy loss.
  arXiv  Detail & Related papers  (2026-05-11T15:57:46Z)
• Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA [71.42483000929614]
  Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents.<n>We propose Doc-$V*$, an textbfOCR-free agentic framework that casts multi-page DocVQA as sequential evidence aggregation.
  arXiv  Detail & Related papers  (2026-04-15T11:12:27Z)
• Lightweight Query Routing for Adaptive RAG: A Baseline Study on RAGRouter-Bench [0.0]
  We present the first systematic evaluation of lightweight classifier-based routing on the benchmark RAG-Bench citepwang2026ragrouterbench.<n>Our best configuration, TF-IDF with an SVM, achieves a macro-averaged F1 of $mathbf0.928$ and an accuracy of $mathbf93.2%$, while simulating $mathbf28.1%$ token savings.
  arXiv  Detail & Related papers  (2026-04-03T20:58:00Z)
• PAR$^2$-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering [57.89576196160413]
  Large language models (LLMs) remain brittle on multi-hop question answering (MHQA)<n>We propose textbfPlanned Active Retrieval and Reasoning RAG (PAR$2$-RAG), a two-stage framework that separates emphcoverage from emphcommitment.
  arXiv  Detail & Related papers  (2026-03-30T23:52:54Z)
• When Agents Disagree: The Selection Bottleneck in Multi-Agent LLM Pipelines [0.0]
  Multi-agent LLM pipelines produce contradictory evidence on whether team diversity improves output quality.<n>We propose a resolution by identifying the selection bottleneck that determines whether diversity helps or hurts.<n>Our results suggest that selector quality may be a more impactful design lever than generator diversity in single-round generate-then-select pipelines.
  arXiv  Detail & Related papers  (2026-03-20T00:50:53Z)
• $G^2$-Reader: Dual Evolving Graphs for Multimodal Document QA [53.491241153213565]
  $G2$-Reader is a dual-graph system for multimodal question answering.<n>$G2$-Reader with Qwen3-VL-32B-Instruct reaches 66.21% average accuracy, outperforming strong baselines and a standalone GPT-5 (53.08%)<n>On VisDoMBench across five multimodal domains, $G2$-Reader with Qwen3-VL-32B-Instruct reaches 66.21% average accuracy, outperforming strong baselines and a standalone GPT-5 (53.08%)
  arXiv  Detail & Related papers  (2026-01-29T17:52:54Z)
• UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG [82.84014669683863]
  Multimodal retrieval-augmented generation (MM-RAG) is a key approach for applying large language models to real-world knowledge bases.<n>UniDoc-Bench is the first large-scale, realistic benchmark for MM-RAG built from 70k real-world PDF pages.<n>Our experiments show that multimodal text-image fusion RAG systems consistently outperform both unimodal and jointly multimodal embedding-based retrieval.
  arXiv  Detail & Related papers  (2025-10-04T04:30:13Z)
• Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering [60.062194349648195]
  Document Visual Question Answering (DocVQA) faces dual challenges in processing lengthy multimodal documents.<n>Current document retrieval-augmented generation (DocRAG) methods remain limited by their text-centric approaches.<n>We introduce MMDocRAG, a comprehensive benchmark featuring 4,055 expert-annotated QA pairs with multi-page, cross-modal evidence chains.
  arXiv  Detail & Related papers  (2025-05-22T09:52:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.