FlowReader：面向长多模态文档证据组装的最小成本流路由

View PDF HTML (experimental)

Abstract:Answering questions about long multimodal documents requires distributing a fixed evidence budget across relevant facets in text, tables, figures, and slides while avoiding near-duplicates. We present \flowreader, which formulates evidence selection as a single minimum-cost flow problem with capacity limits over a multimodal content graph. Spectral decomposition identifies latent aspects of query-relevant content and allocates the budget among them in proportion to their spectral energy. These capacity limits enforce aspect coverage during routing without requiring a language-model planning call. Query-conditioned costs prioritize chains of relevant, mutually consistent evidence. Decomposing the optimal flow produces short evidence chains, which a vision-language model reads in parallel and a reasoner reconciles. On VisDoMBench with Qwen3-VL-32B, \flowreader\ achieves the highest macro accuracy ($68.9$), surpassing the strongest prior system by $2.7$ points, leading on three of five subsets and attaining the highest worst-subset accuracy. It uses a measured $17.5$ content nodes per query and maintains its lead at $12.9$. Ablation studies with a fixed graph, scorer, reader, and judge show that cost design drives accuracy, capacity limits preserve it while using about three-quarters of the reader tokens required by shortest-path routing without these limits on the same network, and spectral aspects align with LLM-generated sub-questions without a planning call.

Subjects:	Information Retrieval (cs.IR); Machine Learning (cs.LG)
Cite as:	arXiv:2606.07235 [cs.IR]
	(or arXiv:2606.07235v3 [cs.IR] for this version)
	https://doi.org/10.48550/arXiv.2606.07235 arXiv-issued DOI via DataCite

Submission history

From: Ambuj Mehrish [view email]
[v1] Fri, 5 Jun 2026 13:05:00 UTC (2,919 KB)
[v2] Mon, 8 Jun 2026 12:31:09 UTC (2,919 KB)
[v3] Fri, 2 Oct 2026 08:18:22 UTC (2,126 KB)