Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AgentRob: From Virtual Forum Agents to Hijacked Physical Robots

Wenrui Liu, Yaxuan Wang, Xun Zhang, Yanshu Wang, Jiashen Wei, Yifan Xiang, Yuhang Wang, Mingshen Ye, Elsie Dai, Zhiqi Liu, Yingjie Xu, Xinyang Chen, Hengzhe Sun, Jiyu Shen, Jingjing He, Tong Yang

TL;DR

AgentRob is presented, a framework that bridges online community forums, LLM-powered agents, and physical robots through the Model Context Protocol (MCP), establishing the feasibility of forum-mediated multi-agent robot orchestration.

Abstract

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.

AgentRob: From Virtual Forum Agents to Hijacked Physical Robots

TL;DR

AgentRob is presented, a framework that bridges online community forums, LLM-powered agents, and physical robots through the Model Context Protocol (MCP), establishing the feasibility of forum-mediated multi-agent robot orchestration.

Abstract

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.
Paper Structure (29 sections, 1 figure, 2 tables, 1 algorithm)

This paper contains 29 sections, 1 figure, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. LLM-based Autonomous Agents
  4. Natural Language Robot Control
  5. Model Context Protocol and Tool-Use Standards
  6. Social Agents in Online Communities
  7. Summary comparison.
  8. System Architecture
  9. Overview
  10. Forum Layer: Forum as Interaction Platform
  11. Agent Layer: MCP-Based Tool Framework
  12. Robot Layer: VLM Controllers and Hardware
  13. Agent Design
  14. LLM-Powered Decision Loop
  15. LLM Provider Abstraction
  16. ...and 14 more sections

Figures (1)

  • Figure 1: Overall architecture of AgentRob. The three-layer design separates forum interaction (Forum Layer), autonomous agent logic (Agent Layer), and robot control with hardware (Robot Layer). Blue arrows ($\downarrow$) denote command flow; red arrows ($\uparrow$) denote result flow.