AgentRob: From Virtual Forum Agents to Hijacked Physical Robots
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917274635468800 |
|---|---|
| author | Liu, Wenrui Wang, Yaxuan Zhang, Xun Wang, Yanshu Wei, Jiashen Xiang, Yifan Wang, Yuhang Ye, Mingshen Dai, Elsie Liu, Zhiqi Xu, Yingjie Chen, Xinyang Sun, Hengzhe Shen, Jiyu He, Jingjing Yang, Tong |
| author_facet | Liu, Wenrui Wang, Yaxuan Zhang, Xun Wang, Yanshu Wei, Jiashen Xiang, Yifan Wang, Yuhang Ye, Mingshen Dai, Elsie Liu, Zhiqi Xu, Yingjie Chen, Xinyang Sun, Hengzhe Shen, Jiyu He, Jingjing Yang, Tong |
| contents | Large Language Model (LLM)-powered autonomous agents have demonstrated significant capabilities in virtual environments, yet their integration with the physical world remains narrowly confined to direct control interfaces. We present AgentRob, a framework that bridges online community forums, LLM-powered agents, and physical robots through the Model Context Protocol (MCP). AgentRob enables a novel paradigm where autonomous agents participate in online forums--reading posts, extracting natural language commands, dispatching physical robot actions, and reporting results back to the community. The system comprises three layers: a Forum Layer providing asynchronous, persistent, multi-agent interaction; an Agent Layer with forum agents that poll for @mention-targeted commands; and a Robot Layer with VLM-driven controllers and Unitree Go2/G1 hardware that translate commands into robot primitives via iterative tool calling. The framework supports multiple concurrent agents with distinct identities and physical embodiments coexisting in the same forum, establishing the feasibility of forum-mediated multi-agent robot orchestration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13591 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AgentRob: From Virtual Forum Agents to Hijacked Physical Robots Liu, Wenrui Wang, Yaxuan Zhang, Xun Wang, Yanshu Wei, Jiashen Xiang, Yifan Wang, Yuhang Ye, Mingshen Dai, Elsie Liu, Zhiqi Xu, Yingjie Chen, Xinyang Sun, Hengzhe Shen, Jiyu He, Jingjing Yang, Tong Robotics Large Language Model (LLM)-powered autonomous agents have demonstrated significant capabilities in virtual environments, yet their integration with the physical world remains narrowly confined to direct control interfaces. We present AgentRob, a framework that bridges online community forums, LLM-powered agents, and physical robots through the Model Context Protocol (MCP). AgentRob enables a novel paradigm where autonomous agents participate in online forums--reading posts, extracting natural language commands, dispatching physical robot actions, and reporting results back to the community. The system comprises three layers: a Forum Layer providing asynchronous, persistent, multi-agent interaction; an Agent Layer with forum agents that poll for @mention-targeted commands; and a Robot Layer with VLM-driven controllers and Unitree Go2/G1 hardware that translate commands into robot primitives via iterative tool calling. The framework supports multiple concurrent agents with distinct identities and physical embodiments coexisting in the same forum, establishing the feasibility of forum-mediated multi-agent robot orchestration. |
| title | AgentRob: From Virtual Forum Agents to Hijacked Physical Robots |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.13591 |