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

• URL: http://arxiv.org/abs/2506.09049v1
• Date: Tue, 10 Jun 2025 17:59:44 GMT
• Title: VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
• Authors: Li Kang, Xiufeng Song, Heng Zhou, Yiran Qin, Jie Yang, Xiaohong Liu, Philip Torr, Lei Bai, Zhenfei Yin,
• Abstract summary: We introduce VIKI-Bench, the first hierarchical benchmark tailored for embodied multi-agent cooperation.<n>VIKI-Bench includes diverse robot embodiments, multi-view visual observations, and structured supervision signals.<n>To demonstrate the utility of VIKI-Bench, we propose VIKI-R, a two-stage framework that fine-tunes a pretrained vision-language model.
• Score: 22.328157991424533
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• A Multi-Granularity Retrieval Framework for Visually-Rich Documents [4.804551482123172]
  We propose a unified multi-granularity multimodal retrieval framework tailored for two benchmark tasks: MMDocIR and M2KR.<n>Our approach integrates hierarchical encoding strategies, modality-aware retrieval mechanisms, and vision-language model (VLM)-based candidate filtering.<n>Our framework demonstrates robust performance without the need for task-specific fine-tuning.
  arXiv  Detail & Related papers  (2025-05-01T02:40:30Z)
• Cooperative Multi-Agent Planning with Adaptive Skill Synthesis [16.228784877899976]
  We present a novel multi-agent architecture that integrates vision-language models (VLMs) with a dynamic skill library and structured communication for decentralized closed-loop decision-making.<n>The skill library, bootstrapped from demonstrations, evolves via planner-guided tasks to enable adaptive strategies.<n>We demonstrate its strong performance against state-of-the-art MARL baselines across both symmetric and asymmetric scenarios.
  arXiv  Detail & Related papers  (2025-02-14T13:23:18Z)
• Instruction-Guided Fusion of Multi-Layer Visual Features in Large Vision-Language Models [50.98559225639266]
  We investigate the contributions of visual features from different encoder layers using 18 benchmarks spanning 6 task categories.<n>Our findings reveal that multilayer features provide complementary strengths with varying task dependencies, and uniform fusion leads to suboptimal performance.<n>We propose the instruction-guided vision aggregator, a module that dynamically integrates multi-layer visual features based on textual instructions.
  arXiv  Detail & Related papers  (2024-12-26T05:41:31Z)
• Unified Generative and Discriminative Training for Multi-modal Large Language Models [88.84491005030316]
  Generative training has enabled Vision-Language Models (VLMs) to tackle various complex tasks. Discriminative training, exemplified by models like CLIP, excels in zero-shot image-text classification and retrieval. This paper proposes a unified approach that integrates the strengths of both paradigms.
  arXiv  Detail & Related papers  (2024-11-01T01:51:31Z)
• VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-use [74.39058448757645]
  We present VipAct, an agent framework that enhances vision-language models (VLMs) VipAct consists of an orchestrator agent, which manages task requirement analysis, planning, and coordination, along with specialized agents that handle specific tasks. We evaluate VipAct on benchmarks featuring a diverse set of visual perception tasks, with experimental results demonstrating significant performance improvements.
  arXiv  Detail & Related papers  (2024-10-21T18:10:26Z)
• Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs [61.143381152739046]
  We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach.<n>Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations.<n>We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes.
  arXiv  Detail & Related papers  (2024-06-24T17:59:42Z)
• Enhancing Human-Centered Dynamic Scene Understanding via Multiple LLMs Collaborated Reasoning [11.526471286502993]
  Video-based Human-Object Interaction (V-HOI) detection is a crucial task in semantic scene understanding. Previous V-HOI detection models have made significant strides in accurate detection on specific datasets. We propose V-HOI Multi-LLMs Collaborated Reasoning (V-HOI MLCR) to facilitate the performance of current V-HOI detection models.
  arXiv  Detail & Related papers  (2024-03-15T08:51:15Z)
• DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention [101.99313208598569]
  Vision-and-language (V-L) tasks require the system to understand both vision content and natural language. We propose DiMBERT (short for Disentangled Multimodal-Attention BERT), which applies separated attention spaces for vision and language. We show that DiMBERT sets new state-of-the-art performance on three tasks.
  arXiv  Detail & Related papers  (2022-10-28T23:00:40Z)
• CH-MARL: A Multimodal Benchmark for Cooperative, Heterogeneous Multi-Agent Reinforcement Learning [15.686200550604815]
  We introduce a benchmark dataset with tasks involving collaboration between multiple simulated heterogeneous robots in a rich multi-room home environment. We provide an integrated learning framework, multimodal implementations of state-of-the-art multi-agent reinforcement learning techniques, and a consistent evaluation protocol.
  arXiv  Detail & Related papers  (2022-08-26T02:21:31Z)
• How to Sense the World: Leveraging Hierarchy in Multimodal Perception for Robust Reinforcement Learning Agents [9.840104333194663]
  We argue for hierarchy in the design of representation models and contribute with a novel multimodal representation model, MUSE. MUSE is the sensory representation model of deep reinforcement learning agents provided with multimodal observations in Atari games. We perform a comparative study over different designs of reinforcement learning agents, showing that MUSE allows agents to perform tasks under incomplete perceptual experience with minimal performance loss.
  arXiv  Detail & Related papers  (2021-10-07T16:35:23Z)
• Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification [208.1227090864602]
  Visible-infrared person re-identification (VI-ReID) is a challenging cross-modality pedestrian retrieval problem. Existing VI-ReID methods tend to learn global representations, which have limited discriminability and weak robustness to noisy images. We propose a novel dynamic dual-attentive aggregation (DDAG) learning method by mining both intra-modality part-level and cross-modality graph-level contextual cues for VI-ReID.
  arXiv  Detail & Related papers  (2020-07-18T03:08:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.