Towards the Harness of Embodied Agents

Qi Wang, Tianyi Wang, Chengyang Li, Shikun Ban, Yurun Chen,
Yizhong Ge, Jason Qin, Chengtai Li, Wentao Zhu

Eastern Institute of Technology, Ningbo

 Core contributors

TL;DR: Thea brings coding agents to the physical world.

Instruction“Grab me a water.”

0:00 / 0:00
Watch the full demo (5:44) on YouTube or Bilibili.

Abstract

The success of coding agents has established the harness as a paradigm: what an agent achieves depends not on the model alone, but on the infrastructure around it. We ask whether the same paradigm extends to embodied agents in the physical world. We present Thea, a harness in which an agentic loop orchestrates robot capabilities, each wrapped as a callable tool. It inherits the core components of coding agents, modified as the physical world requires. The world, however, withholds two abilities that software grants for free: reading the state of the world, and judging the outcome of an action. To bridge these gaps, Thea introduces Scene Graph as Context, a persistent, symbolic representation of the world, and Evaluation as Exit Codes, which detects when an action should terminate, judges whether it succeeded, and on failure diagnoses the cause. Together they close the loop between the agent and the physical world. Rich behaviors then emerge from the composition of tools, and the closed loop carries long-horizon tasks to completion in real environments.

Citation

@misc{thea2026,
  title  = {Towards the Harness of Embodied Agents},
  author = {Qi Wang and Tianyi Wang and Chengyang Li and Shikun Ban and Yurun Chen
            and Yizhong Ge and Jason Qin and Chengtai Li and Wentao Zhu},
  year   = {2026},
  note   = {Technical Report},
}