SAGE is a multi‑agent framework that transforms Chinese ancient document understanding from direct answer generation into evidence‑grounded inference. It orchestrates specialized agents for planning, evidence acquisition, claim verification, and bounded replanning within a shared‑state runtime, enabling evidence seeking, answer revision, and abstention when grounding is lacking. Experiments on the AncientDoc benchmark show that SAGE outperforms direct‑answering baselines across three LVLM backbones, and even a 9B‑parameter Qwen3.5 model surpasses larger monolithic LVLMs, underscoring the value of structured, evidence‑grounded inference over mere model scaling.
By Yuchuan Wu, Xuan Luo, Yinglian Zhu, Meng Fang, Xiangyang Xue, Bin Li
DocPilot is an agentic framework for long visual document understanding that orchestrates evidence seeking through page-level navigation and fine-grained localization, integrating visual inspection, code-based numerical reasoning, and cross-modal reasoning. It employs curriculum-based agentic training to enable small language models to learn complex document solving, progressing from single-ability learning to adaptive orchestration. Experiments on benchmarks such as MMLongBench-Doc, DocBench, FinRAGBench-V, and MADQA show that DocPilot achieves strong gains with frontier VLM backbones, and its 4B variant competes with much larger models, demonstrating effectiveness and generalization across diverse long-document reasoning tasks.
By Zhuowen Liang, Xiaotian Lin, Yuyu Luo, Haixun Wang, Nan Tang
arXiv:2604. 13731v2 Announce Type: replace Abstract: Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents.
By Yuanlei Zheng, Pei Fu, Hang Li, Ziyang Wang, Yuyi Zhang, Wenyu Ruan, Xiaojin Zhang, Zhongyu Wei, Zhenbo Luo, Jian Luan, Wei Chen, Xiang Bai
VELD-QA is a large-scale benchmark for visual evidence grounding and question answering in long documents, comprising 15,000 human-authored question-answer pairs across 5,859 PDFs with 372,445 pages. The dataset includes detailed annotations of supporting pages, visual evidence elements, and descriptions of cited visual content, enabling separate evaluation of retrieval, localization, and interpretation. Experiments on nine vision-language models and various retrieval-augmented systems reveal significant gaps in evidence localization and visual interpretation, with oracle accuracy peaking at 81.7% and enrichment of visual-element annotations narrowing performance gaps by 17–24%.
By Zhivar Sourati, Marianne Menglin Liu, Rongguang Wang, Zheng Wang, Yazhe Hu, Lan Guo, Yuying Wang, Mengqing Guo, Bhavesh Dnyaneshwar Gore, Shubham Pathak, Ramapriya Ranganath, Sandeep Sharma, Tao Sheng, Sujith Ravi, Dan Roth
arXiv:2608. 03292v1 Announce Type: new Abstract: Long Document Visual Question Answering (LongDocVQA) requires Multimodal Large Language Models (MLLMs) to locate, integrate, and reason over heterogeneous document elements distributed across multiple pages.
By Le Xiang, Zhicheng Guan, Hong Chen, Xiaocong Lin, Zhenghua Lei, Teng Hu, Bolei He, Long Zeng
The paper introduces TerraAgent, a training‑free framework that enhances remote sensing visual question answering by integrating three modules: GDR for demonstration retrieval, MACE for evidence‑typed sub‑question decomposition, and CVA for counterfactual evidence auditing. It demonstrates significant improvements on multiple benchmarks, raising accuracy, visual‑dependency scores, and reducing prior‑only answers and hallucinations without fine‑tuning.
By Jingwen Huang, Yiming Fang, Hanxiao Wu, Boyuan He, Keyi Luo
arXiv:2608. 08021v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) should answer from concrete image evidence rather than language priors, dataset shortcuts, or irrelevant visual context.
By Haojie Huang, Xinlei Yu, Chengming Xu, Zhangquan Chen, Cheng Yang, Qingdong He, Yu Yang, Jiangning Zhang, Xiaobin Hu
arXiv:2606. 29984v1 Announce Type: new Abstract: Reinforcement Learning (RL) is an important paradigm for improving the reasoning capabilities of Vision-Language Models (VLMs).
By Peng, Lee, Yin Zhang, Yanglin Zhang, Haonan Wu, Zishan Liu, Ruoxi Zang, Xin Zhu, Jiayin Zheng, Jian Yao, Zefeng Ji, Fei Ma
The paper introduces FoG, a framework that trains knowledge graph (KG) agents to retrieve the evidence behind their answers. FoG combines evidence‑grounded synthesis, a KG interaction agent, and an evidence‑coverage process reward (ECPR) to ensure that every answer is supported by retrieved triples. Experiments on three KGQA benchmarks show that 3B–4B open‑source agents trained with FoG outperform larger baselines in both answer accuracy and evidence coverage, even with zero‑shot cross‑KG transfer.
By Zongyuan Sun, Shuai Zhao, Yingjun Du, Ke Shu, Ziyue Zhu, Haoran Luo
Vision-Language Models (VLMs) still struggle on tasks requiring complex visual understanding. We argue that the core issue is not high-level reasoning, but instead failing to locate critical details i...
Multimodal agents for visual question answering increasingly operate as multi-step trajectories that interleave perception, retrieval, and reasoning, yet evaluation still largely reduces to final-answer accuracy. This aggregate signal cannot tell whether a correct answer was reached through grounded evidence, language priors, or accidental error cancellation.
arXiv:2604. 22565v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can reason well, yet often miss decisive evidence when it is buried in long, noisy contexts.
By Shaoang Li, Yanhang Shi, Yufei Li, Mingfu Liang, Xiaohan Wei, Yunchen Pu, Fei Tian, Chonglin Sun, Frank Shyu, Luke Simon, Sandeep Pandey, Xi Liu, Jian Li