arXiv 2506.090492026-01-22cs.AIcs.CVcs.RO

VIKI-R: 通过强化学习协调具身多智能体合作

VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning

Shanghai Jiao Tong University（上海交通大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；University of Science and Technology of China（中国科学技术大学）；University of Oxford（牛津大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））

Li Kang, Xiufeng Song, Heng Zhou, Yiran Qin, Jie Yang, Xiaohong Liu, Philip Torr, Lei Bai, Zhenfei Yin

备注：: Accepted by NeurIPS 2025 Track on Datasets and Benchmarks. Project page: https://faceong.github.io/VIKI-R/

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

VIKI-R通过强化学习协调多智能体合作，提出分层基准VIKI-Bench，显著提升多智能体视觉驱动合作性能。

摘要：

在动态环境中协调多个具身智能体仍然是人工智能中的核心挑战，需要基于感知的推理和可扩展的合作策略。尽管近期的工作已经利用大语言模型（LLMs）进行多智能体规划，但一些研究开始探索视觉语言模型（VLMs）进行视觉推理。然而，这些基于VLM的方法在支持多样化具身类型方面仍然有限。在本工作中，我们引入了VIKI-Bench，这是首个针对具身多智能体合作设计的分层基准，包含三个结构化层次：智能体激活、任务规划和轨迹感知。VIKI-Bench包含多样化的机器人具身、多视角视觉观测和结构化的监督信号，以评估基于视觉输入的推理。为了展示VIKI-Bench的实用性，我们提出了VIKI-R，一个两阶段框架，通过链式推理注释演示微调预训练的视觉语言模型（VLM），随后在多级奖励信号下进行强化学习。我们的广泛实验表明，VIKI-R在所有任务层次上均显著优于基线方法。此外，我们还表明强化学习能够使异质智能体之间产生组合性合作模式。共同，VIKI-Bench和VIKI-R为推进具身人工智能系统中的多智能体、视觉驱动合作提供了统一的测试平台和方法。

英文摘要：

Coordinating multiple embodied agents in dynamic environments remains a core challenge in artificial intelligence, requiring both perception-driven reasoning and scalable cooperation strategies. While recent works have leveraged large language models (LLMs) for multi-agent planning, a few have begun to explore vision-language models (VLMs) for visual reasoning. However, these VLM-based approaches remain limited in their support for diverse embodiment types. In this work, we introduce VIKI-Bench, the first hierarchical benchmark tailored for embodied multi-agent cooperation, featuring three structured levels: agent activation, task planning, and trajectory perception. VIKI-Bench includes diverse robot embodiments, multi-view visual observations, and structured supervision signals to evaluate reasoning grounded in visual inputs. To demonstrate the utility of VIKI-Bench, we propose VIKI-R, a two-stage framework that fine-tunes a pretrained vision-language model (VLM) using Chain-of-Thought annotated demonstrations, followed by reinforcement learning under multi-level reward signals. Our extensive experiments show that VIKI-R significantly outperforms baselines method across all task levels. Furthermore, we show that reinforcement learning enables the emergence of compositional cooperation patterns among heterogeneous agents. Together, VIKI-Bench and VIKI-R offer a unified testbed and method for advancing multi-agent, visual-driven cooperation in embodied AI systems.

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。