Ella: Embodied Social Agents with Lifelong Memory
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_ | 1866916817527635968 |
|---|---|
| author | Zhang, Hongxin Zhang, Zheyuan Wang, Zeyuan Zhang, Zunzhe Fang, Lixing Zhou, Qinhong Gan, Chuang |
| author_facet | Zhang, Hongxin Zhang, Zheyuan Wang, Zeyuan Zhang, Zunzhe Fang, Lixing Zhou, Qinhong Gan, Chuang |
| contents | We introduce Ella, an embodied social agent capable of lifelong learning within a community in a 3D open world, where agents accumulate experiences and acquire knowledge through everyday visual observations and social interactions. At the core of Ella's capabilities is a structured, long-term multimodal memory system that stores, updates, and retrieves information effectively. It consists of a name-centric semantic memory for organizing acquired knowledge and a spatiotemporal episodic memory for capturing multimodal experiences. By integrating this lifelong memory system with foundation models, Ella retrieves relevant information for decision-making, plans daily activities, builds social relationships, and evolves autonomously while coexisting with other intelligent beings in the open world. We conduct capability-oriented evaluations in a dynamic 3D open world where 15 agents engage in social activities for days and are assessed with a suite of unseen controlled evaluations. Experimental results show that Ella can influence, lead, and cooperate with other agents well to achieve goals, showcasing its ability to learn effectively through observation and social interaction. Our findings highlight the transformative potential of combining structured memory systems with foundation models for advancing embodied intelligence. More videos can be found at https://umass-embodied-agi.github.io/Ella/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_24019 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ella: Embodied Social Agents with Lifelong Memory Zhang, Hongxin Zhang, Zheyuan Wang, Zeyuan Zhang, Zunzhe Fang, Lixing Zhou, Qinhong Gan, Chuang Computer Vision and Pattern Recognition Computation and Language We introduce Ella, an embodied social agent capable of lifelong learning within a community in a 3D open world, where agents accumulate experiences and acquire knowledge through everyday visual observations and social interactions. At the core of Ella's capabilities is a structured, long-term multimodal memory system that stores, updates, and retrieves information effectively. It consists of a name-centric semantic memory for organizing acquired knowledge and a spatiotemporal episodic memory for capturing multimodal experiences. By integrating this lifelong memory system with foundation models, Ella retrieves relevant information for decision-making, plans daily activities, builds social relationships, and evolves autonomously while coexisting with other intelligent beings in the open world. We conduct capability-oriented evaluations in a dynamic 3D open world where 15 agents engage in social activities for days and are assessed with a suite of unseen controlled evaluations. Experimental results show that Ella can influence, lead, and cooperate with other agents well to achieve goals, showcasing its ability to learn effectively through observation and social interaction. Our findings highlight the transformative potential of combining structured memory systems with foundation models for advancing embodied intelligence. More videos can be found at https://umass-embodied-agi.github.io/Ella/. |
| title | Ella: Embodied Social Agents with Lifelong Memory |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2506.24019 |