DocLens : A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding
Comprehending long visual documents, where information is distributed across extensive pages of text and visual elements, is a critical but challenging task for modern Vision-Language Models (VLMs). Existing approaches falter on a fundamental challenge: evidence localization. They struggle to retrieve relevant pages and overlook fine-grained details within visual elements, leading to limited performance and model hallucination. To address this, we propose DocLens, a tool-augmented multi-agent framework that effectively ``zooms in'' on evidence like a lens. It first navigates from the full document to specific visual elements on relevant pages, then employs a sampling-adjudication mechanism to generate a single, reliable answer. Paired with Gemini-2.5-Pro, DocLens achieves state-of-the-art performance on MMLongBench-Doc and FinRAGBench-V, surpassing even human experts. The framework's superiority is particularly evident on vision-centric and unanswerable queries, demonstrating the power of its enhanced localization capabilities.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
DocLens: Multi-aspect Fine-grained Evaluation for Medical Text Generation
Medical text generation aims to assist with administrative work and highlight salient information to support decision-making. To reflect the specific requirements of medical text, in this paper, we propose a set of metri…
Decision MakingInstruction FollowingText GenerationWhen Users Are Happy but Agents Are Wrong: Multi-Dimensional Evaluation of Tool-Augmented Dialogue
Evaluating conversational AI systems that use external tools is challenging, as errors can arise from complex interactions among user, agent, and tools. While existing evaluation methods assess either user satisfaction o…
PDE-Agent: A toolchain-augmented multi-agent framework for PDE solving
Solving Partial Differential Equations (PDEs) is a cornerstone of engineering and scientific research. Traditional methods for PDE solving are cumbersome, relying on manual setup and domain expertise. While Physics-Infor…
Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents
Although recent tool-augmented benchmarks involve complex requests, evaluation remains limited to answer matching, neglecting critical trajectory aspects like efficiency, hallucination, and adaptivity. The most straightf…
Time Series Augmented Generation for Financial Applications
Evaluating the reasoning capabilities of Large Language Models (LLMs) for complex, quantitative financial tasks is a critical and unsolved challenge. Standard benchmarks often fail to isolate an agent's core ability to p…