VULCAN：面向迭代式三维物体布局的工具增强多智能体
VULCAN: Tool-Augmented Multi Agents for Iterative 3D Object Arrangement
把 MLLM 的 3D 操作能力从脆弱的原始代码生成转为函数级 API 调用，并引入视觉工具构成感知反馈闭环，为视觉研究者提供了一条「用工具调用弥补 MLLM 3D 视觉定位短板」的可复用范式。
原文依据 we introduce an MCP-based API. This shifts the interaction from brittle raw code manipulation to more robust, function-level updates
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论尽管多模态大语言模型（MLLM）在二维视觉语言任务上取得了显著进展，但其在复杂三维场景操作中的应用仍未被充分探索。本文通过利用 MLLM 应对三维物体布局任务中的三个关键挑战，填补了这一重要空白。首先，针对 MLLM 视觉定位能力薄弱、难以将程序化编辑与精确三维结果对应起来的问题，我们引入了一套基于 MCP 的 API。这将交互方式从脆弱的原始代码操作转变为更稳健的函数级更新。其次，我们用一套专门的视觉工具增强 MLLM 的三维场景理解能力，用于分析场景状态、收集空间信息并验证动作结果。这一感知反馈闭环对于弥合基于语言的更新与精确的三维感知操作之间的差距至关重要。第三，为管理迭代式且易出错的更新过程，我们提出了一个协作式多智能体框架，为规划、执行与验证分配了明确的角色。这种分解使系统能够稳健地处理多步指令并从中间错误中恢复。我们在 25 项复杂物体布局任务上验证了该方法的有效性，其性能显著优于现有基线。
英文原文摘要 1303 字符
Despite the remarkable progress of Multimodal Large Language Models (MLLMs) in 2D vision-language tasks, their application to complex 3D scene manipulation remains underexplored. In this paper, we bridge this critical gap by tackling three key challenges in 3D object arrangement task using MLLMs. First, to address the weak visual grounding of MLLMs, which struggle to link programmatic edits with precise 3D outcomes, we introduce an MCP-based API. This shifts the interaction from brittle raw code manipulation to more robust, function-level updates. Second, we augment the MLLM's 3D scene understanding with a suite of specialized visual tools to analyze scene state, gather spatial information, and validate action outcomes. This perceptual feedback loop is critical for closing the gap between language-based updates and precise 3D-aware manipulation. Third, to manage the iterative, error-prone updates, we propose a collaborative multi-agent framework with designated roles for planning, execution, and verification. This decomposition allows the system to robustly handle multi-step instructions and recover from intermediate errors. We demonstrate the effectiveness of our approach on a diverse set of 25 complex object arrangement tasks, where it significantly outperforms existing baselines.