Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908472507891712 |
|---|---|
| author | Hong, Yining Sun, Rui Li, Bingxuan Yao, Xingcheng Wu, Maxine Chien, Alexander Yin, Da Wu, Ying Nian Wang, Zhecan James Chang, Kai-Wei |
| author_facet | Hong, Yining Sun, Rui Li, Bingxuan Yao, Xingcheng Wu, Maxine Chien, Alexander Yin, Da Wu, Ying Nian Wang, Zhecan James Chang, Kai-Wei |
| contents | AI agents today are mostly siloed - they either retrieve and reason over vast amount of digital information and knowledge obtained online; or interact with the physical world through embodied perception, planning and action - but rarely both. This separation limits their ability to solve tasks that require integrated physical and digital intelligence, such as cooking from online recipes, navigating with dynamic map data, or interpreting real-world landmarks using web knowledge. We introduce Embodied Web Agents, a novel paradigm for AI agents that fluidly bridge embodiment and web-scale reasoning. To operationalize this concept, we first develop the Embodied Web Agents task environments, a unified simulation platform that tightly integrates realistic 3D indoor and outdoor environments with functional web interfaces. Building upon this platform, we construct and release the Embodied Web Agents Benchmark, which encompasses a diverse suite of tasks including cooking, navigation, shopping, tourism, and geolocation - all requiring coordinated reasoning across physical and digital realms for systematic assessment of cross-domain intelligence. Experimental results reveal significant performance gaps between state-of-the-art AI systems and human capabilities, establishing both challenges and opportunities at the intersection of embodied cognition and web-scale knowledge access. All datasets, codes and websites are publicly available at our project page https://embodied-web-agent.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_15677 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence Hong, Yining Sun, Rui Li, Bingxuan Yao, Xingcheng Wu, Maxine Chien, Alexander Yin, Da Wu, Ying Nian Wang, Zhecan James Chang, Kai-Wei Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Multimedia Robotics AI agents today are mostly siloed - they either retrieve and reason over vast amount of digital information and knowledge obtained online; or interact with the physical world through embodied perception, planning and action - but rarely both. This separation limits their ability to solve tasks that require integrated physical and digital intelligence, such as cooking from online recipes, navigating with dynamic map data, or interpreting real-world landmarks using web knowledge. We introduce Embodied Web Agents, a novel paradigm for AI agents that fluidly bridge embodiment and web-scale reasoning. To operationalize this concept, we first develop the Embodied Web Agents task environments, a unified simulation platform that tightly integrates realistic 3D indoor and outdoor environments with functional web interfaces. Building upon this platform, we construct and release the Embodied Web Agents Benchmark, which encompasses a diverse suite of tasks including cooking, navigation, shopping, tourism, and geolocation - all requiring coordinated reasoning across physical and digital realms for systematic assessment of cross-domain intelligence. Experimental results reveal significant performance gaps between state-of-the-art AI systems and human capabilities, establishing both challenges and opportunities at the intersection of embodied cognition and web-scale knowledge access. All datasets, codes and websites are publicly available at our project page https://embodied-web-agent.github.io/. |
| title | Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence |
| topic | Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Multimedia Robotics |
| url | https://arxiv.org/abs/2506.15677 |