BEAR: Benchmarking and Enhancing Multimodal Language Models for Atomic Embodied Capabilities

• URL: http://arxiv.org/abs/2510.08759v1
• Date: Thu, 09 Oct 2025 19:18:36 GMT
• Title: BEAR: Benchmarking and Enhancing Multimodal Language Models for Atomic Embodied Capabilities
• Authors: Yu Qi, Haibo Zhao, Ziyu Guo, Siyuan Ma, Ziyan Chen, Yaokun Han, Renrui Zhang, Zitiantao Lin, Shiji Xin, Yijian Huang, Kai Cheng, Peiheng Wang, Jiazheng Liu, Jiayi Zhang, Yizhe Zhu, Wenqing Wang, Yiran Qin, Xupeng Zhu, Haojie Huang, Lawson L. S. Wong,
• Abstract summary: Embodied capabilities refer to a suite of fundamental abilities for an agent to perceive, comprehend, and interact with the physical world.<n>We introduce BEAR, a comprehensive and fine-grained benchmark that evaluates MLLMs on atomic embodied capabilities.<n> BEAR comprises 4,469 interleaved image-video-text entries across 14 domains in 6 categories, including tasks from low-level pointing, trajectory understanding, spatial reasoning, to high-level planning.<n>We propose BEAR-Agent, a multimodal conversable agent that integrates pretrained vision models to strengthen MLLM perception, 3D understanding, and planning capabilities.
• Score: 61.173773299032746
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Embodied capabilities refer to a suite of fundamental abilities for an agent to perceive, comprehend, and interact with the physical world. While multimodal large language models (MLLMs) show promise as embodied agents, a thorough and systematic evaluation of their embodied capabilities remains underexplored, as existing benchmarks primarily focus on specific domains such as planning or spatial understanding. To bridge this gap, we introduce BEAR, a comprehensive and fine-grained benchmark that evaluates MLLMs on atomic embodied capabilities. BEAR comprises 4,469 interleaved image-video-text entries across 14 domains in 6 categories, including tasks from low-level pointing, trajectory understanding, spatial reasoning, to high-level planning. Extensive evaluation results of 20 representative MLLMs reveal their persistent limitations across all domains of embodied capabilities. To tackle the shortfall, we propose BEAR-Agent, a multimodal conversable agent that integrates pretrained vision models to strengthen MLLM perception, 3D understanding, and planning capabilities. It substantially enhances MLLM performance across diverse embodied capabilities on BEAR, yielding a 9.12% absolute gain and a relative improvement of 17.5% on GPT-5. Furthermore, our experiments indicate that improving MLLM embodied capabilities can benefit embodied tasks in simulated environments. Project website: https://bear-official66.github.io/

Related papers

• Holistic Evaluation of Multimodal LLMs on Spatial Intelligence [81.2547965083228]
  We propose EASI for holistic Evaluation of multimodAl LLMs on Spatial Intelligence.<n>We conduct the study across eight key benchmarks, at a cost exceeding ten billion total tokens.<n>Our empirical study then reveals that GPT-5 demonstrates unprecedented strength in spatial intelligence (SI), yet (2) still falls short of human performance significantly across a broad spectrum of SI-tasks.
  arXiv  Detail & Related papers  (2025-08-18T17:55:17Z)
• On Path to Multimodal Generalist: General-Level and General-Bench [153.9720740167528]
  This project introduces General-Level, an evaluation framework that defines 5-scale levels of MLLM performance and generality.<n>At the core of the framework is the concept of Synergy, which measures whether models maintain consistent capabilities across comprehension and generation.<n>The evaluation results that involve over 100 existing state-of-the-art MLLMs uncover the capability rankings of generalists.
  arXiv  Detail & Related papers  (2025-05-07T17:59:32Z)
• EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents [63.43699771428243]
  EmbodiedBench is an extensive benchmark designed to evaluate vision-driven embodied agents.<n>We evaluated 24 leading proprietary and open-source MLLMs within EmbodiedBench.<n> MLLMs excel at high-level tasks but struggle with low-level manipulation, with the best model, GPT-4o, scoring only 28.9% on average.
  arXiv  Detail & Related papers  (2025-02-13T18:11:34Z)
• EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents [57.4686961979566]
  EmbodiedEval is a comprehensive and interactive evaluation benchmark for MLLMs with embodied tasks.<n>It covers a broad spectrum of existing embodied AI tasks with significantly enhanced diversity.<n>We evaluated the state-of-the-art MLLMs on EmbodiedEval and found that they have a significant shortfall compared to human level on embodied tasks.
  arXiv  Detail & Related papers  (2025-01-21T03:22:10Z)
• Grounding Multimodal Large Language Models in Actions [65.88208317380793]
  We study how to best ground a MLLM into different embodiments and their associated action spaces.<n>For continuous actions, we show that a learned tokenization allows for sufficient modeling precision.<n>For discrete actions, we demonstrate that semantically aligning these actions with the native output token space of the MLLM leads to the strongest performance.
  arXiv  Detail & Related papers  (2024-06-12T06:12:04Z)

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.