Salvato in:
Dettagli Bibliografici
Autori principali: Yu, Xinlei, Xu, Chengming, Chen, Zhangquan, Zhang, Yudong, Lu, Shilin, Yang, Cheng, Zhang, Jiangning, Yan, Shuicheng, Hu, Xiaobin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2508.03404
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909901354172416
author Yu, Xinlei
Xu, Chengming
Chen, Zhangquan
Zhang, Yudong
Lu, Shilin
Yang, Cheng
Zhang, Jiangning
Yan, Shuicheng
Hu, Xiaobin
author_facet Yu, Xinlei
Xu, Chengming
Chen, Zhangquan
Zhang, Yudong
Lu, Shilin
Yang, Cheng
Zhang, Jiangning
Yan, Shuicheng
Hu, Xiaobin
contents The dominant paradigm of monolithic scaling in Vision-Language Models (VLMs) is failing for understanding and reasoning in documents, yielding diminishing returns as it struggles with the inherent need of this domain for document-based procedural reasoning, cognitive complexity, and factual accuracy. To this end, we introduce MACT, a Multi-Agent Collaboration framework with agent-wise adaptive Test-time scaling that pioneers a paradigm shift to procedural scaling, adapting dynamically to the functional entities of visual documents understanding and reasoning. MACT decomposes the visual document processing flow into four specialized agents, i.e., planning, execution, judgment, and answer, to resolve cognitive overload and introduce a critical self-correction loop for factual grounding. This collaborative architecture is amplified by an agent-wise adaptive test-time scaling strategy that intelligently allocates computational resources based on the complexity and redundancy of each functionality. Evaluated on multiple visual document understanding benchmarks, MACT achieves superior performance with a smaller parameter scale, adapting effectively to various document scenarios without compromising its general or mathematical reasoning capabilities. The three variants of MACT consistently attain top-three average performance rankings, with average performance enhancements of 9.9-11.5% over the base models. The source code will be released publicly.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03404
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scaling
Yu, Xinlei
Xu, Chengming
Chen, Zhangquan
Zhang, Yudong
Lu, Shilin
Yang, Cheng
Zhang, Jiangning
Yan, Shuicheng
Hu, Xiaobin
Computer Vision and Pattern Recognition
Artificial Intelligence
The dominant paradigm of monolithic scaling in Vision-Language Models (VLMs) is failing for understanding and reasoning in documents, yielding diminishing returns as it struggles with the inherent need of this domain for document-based procedural reasoning, cognitive complexity, and factual accuracy. To this end, we introduce MACT, a Multi-Agent Collaboration framework with agent-wise adaptive Test-time scaling that pioneers a paradigm shift to procedural scaling, adapting dynamically to the functional entities of visual documents understanding and reasoning. MACT decomposes the visual document processing flow into four specialized agents, i.e., planning, execution, judgment, and answer, to resolve cognitive overload and introduce a critical self-correction loop for factual grounding. This collaborative architecture is amplified by an agent-wise adaptive test-time scaling strategy that intelligently allocates computational resources based on the complexity and redundancy of each functionality. Evaluated on multiple visual document understanding benchmarks, MACT achieves superior performance with a smaller parameter scale, adapting effectively to various document scenarios without compromising its general or mathematical reasoning capabilities. The three variants of MACT consistently attain top-three average performance rankings, with average performance enhancements of 9.9-11.5% over the base models. The source code will be released publicly.
title Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scaling
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2508.03404