ORCA：用于文档视觉问答的协作代理协同推理
ORCA: Orchestrated Reasoning with Collaborative Agents for Document Visual Question Answering
AI总结：
ORCA通过协作代理协同推理提升文档视觉问答的复杂推理与多步骤工作流处理能力。
摘要：
文档视觉问答（DocVQA）仍对现有视觉-语言模型（VLMs）构成挑战，特别是在复杂推理和多步骤工作流下。当前方法难以将复杂问题分解为可管理的子任务，且往往无法利用专门处理路径来处理不同文档元素。我们提出了ORCA：用于文档视觉问答的协作代理协同推理，一种新的多代理框架，通过战略代理协调和迭代优化来解决这些限制。ORCA首先由一个推理代理将查询分解为逻辑步骤，随后由路由机制激活从专用代理码头中选取的任务特定代理。我们的框架利用一组专门的AI代理，每个代理专注于不同的模态，从而在多样化的文档组件上实现细粒度理解和协同推理。为确保回答的可靠性，ORCA采用具有压力测试的辩论机制，并在必要时采用论点-反论点裁决过程。随后是一个 sanity 检查器以确保格式一致性。在三个基准上的广泛实验表明，我们的方法在现有最先进方法上取得了显著改进，建立了协作代理系统在视觉-语言推理中的新范式。
英文摘要：
Document Visual Question Answering (DocVQA) remains challenging for existing Vision-Language Models (VLMs), especially under complex reasoning and multi-step workflows. Current approaches struggle to decompose intricate questions into manageable sub-tasks and often fail to leverage specialized processing paths for different document elements. We present ORCA: Orchestrated Reasoning with Collaborative Agents for Document Visual Question Answering, a novel multi-agent framework that addresses these limitations through strategic agent coordination and iterative refinement. ORCA begins with a reasoning agent that decomposes queries into logical steps, followed by a routing mechanism that activates task-specific agents from a specialized agent dock. Our framework leverages a set of specialized AI agents, each dedicated to a distinct modality, enabling fine-grained understanding and collaborative reasoning across diverse document components. To ensure answer reliability, ORCA employs a debate mechanism with stress-testing, and when necessary, a thesis-antithesis adjudication process. This is followed by a sanity checker to ensure format consistency. Extensive experiments on three benchmarks demonstrate that our approach achieves significant improvements over state-of-the-art methods, establishing a new paradigm for collaborative agent systems in vision-language reasoning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
