Towards the Harness of Embodied Agents
Summary
Presents Thea, a harness for embodied agents that orchestrates robot capabilities as callable tools, introducing Scene Graph as Context and Evaluation as Exit Codes to close the loop between agent and physical world.
View Cached Full Text
Cached at: 08/13/26, 03:24 PM
# Towards the Harness of Embodied Agents Source: [https://arxiv.org/abs/2608.11246](https://arxiv.org/abs/2608.11246) [View PDF](https://arxiv.org/pdf/2608.11246) > 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\. ## Submission history From: Wentao Zhu \[[view email](https://arxiv.org/show-email/cfaa6cfa/2608.11246)\] **\[v1\]**Mon, 3 Aug 2026 09:19:38 UTC \(2,645 KB\)
Similar Articles
Harness Handbook to Map Agent Behavior to Code (28 minute read)
Harness Handbook provides a behavior-level manual for AI agent harnesses, linking system behaviors to verifiable code evidence to make harnesses understandable, auditable, and editable.
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
The Harness Handbook is a behavior-centric representation synthesized from agent harness codebases using static program analysis and LLM assistance, helping developers and coding agents locate code implementing specific behaviors. It introduces Behavior-Guided Progressive Disclosure (BGPD) to guide agents from high-level descriptions to relevant implementation details, improving localization accuracy and edit-plan quality.
Code as Agent Harness
This survey paper presents a unified view of code as the operational substrate for agent reasoning and execution in agentic systems, organizing the discussion around three layers: harness interface, mechanisms, and scaling.
The Evolution of the Agent Harness (10 minute read)
The article discusses how the simultaneous evolution of AI models and harnesses has led to significant improvements in agent capabilities, shifting the harness's role to focus on human attention interfaces.
@omarsar0: // Self-Harness: Harnesses That Improve Themselves // (bookmark this one) Most of the agent scaffolds we rely on today …
This paper introduces Self-Harness, a new paradigm where LLM-based agents iteratively improve their own operating harness—prompts, tools, and control flow—without human engineers or stronger external agents, achieving significant performance gains across multiple models.