# EMHO: EMbodied Agent Harness Optimization via Experience Traces

arXiv: https://arxiv.org/abs/2610.08432 · HTML: https://mlsanity.com/paper/2610.08432/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 11 of 11)

- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses](https://mlsanity.com/paper/2604.25850/) (2026)
- [Self-Harness: Harnesses That Improve Themselves](https://mlsanity.com/paper/2606.09498/) (2026)
- [ASPIRE: Agentic /Skills Discovery for Robotics](https://mlsanity.com/paper/2607.00272/) (2026)
- [OK-Robot: What Really Matters in Integrating Open-Knowledge Models for Robotics](https://mlsanity.com/paper/2401.12202/) (2024)
- [EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents](https://mlsanity.com/paper/2605.10332/) (2026)
- [AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces](https://mlsanity.com/paper/2608.23041/) (2026)
- [Zetta zeta: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence](https://mlsanity.com/paper/2608.16590/) (2026)
- [VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents](https://mlsanity.com/paper/2606.05395/) (2026)
- [Enabling Extensible Embodied Capabilities with Tools](https://mlsanity.com/paper/2605.26637/) (2026)

## Built on by (most cited first, 1 of 1)

- [Self-Evolving Agent Harness](https://mlsanity.com/paper/2610.18813/) (2026)

## Abstract (arXiv)

Improving embodied agents often focuses on optimizing the underlying model through training, while the surrounding agent harness that controls planning, context, and tool use is typically engineered. We ask whether this harness can instead improve itself directly from experience traces under sparse environmental feedback. We propose EMbodied Agent Harness Optimization (EMHO), a self-evolving framework that keeps the embodied model frozen and iteratively revises its harness by analyzing execution trajectories and prior harness history. EMHO optimizes beyond skills or recovery prompts, modifying how the agent monitors progress, uses vision tools, grounds observations, and responds to failures. To support multiple subtasks with a single harness, we introduce EMHO-Merge, which addresses trade-offs in jointly optimizing a single shared harness across subtasks by using episode-level gains and losses to guide evidence-supported refinement of when and how revised behaviors are applied. We evaluate EMHO on EmbodiedBench across navigation and manipulation tasks, and EMHO consistently improves task success for both Qwen 9B and 27B models. Qualitative analysis shows that EMHO goes beyond recovering from failures and unproductive actions to reshape how the embodied agent interprets and interacts with its environment.