EMHO: EMbodied Agent Harness Optimization via Experience Traces

Hugging Face Daily Papers Papers
embodied-agents self-evolving-harness robotics planning tool-use reinforcement-from-traces

Summary

EMHO 提出一种自进化框架，在冻结具身模型的前提下，通过分析执行轨迹与历史经验自动迭代优化 agent harness（规划、上下文与工具使用），并在 EmbodiedBench 的导航与操作任务上一致提升 Qwen 9B/27B 的任务成功率。

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.
Original Article
View Cached Full Text

Cached at: 10/14/26, 02:53 PM

Paper page - EMHO: EMbodied Agent Harness Optimization via Experience Traces

Source: https://huggingface.co/papers/2610.08432

Abstract

Improvingembodiedagentsoftenfocusesonoptimizingtheunderlyingmodelthroughtraining,whilethesurroundingagentharnessthatcontrolsplanning,context,andtooluseistypicallyengineered.Weaskwhetherthisharnesscaninsteadimproveitselfdirectlyfromexperiencetracesundersparseenvironmentalfeedback.WeproposeEMbodiedAgentHarnessOptimization(EMHO),aself-evolvingframeworkthatkeepstheembodiedmodelfrozenanditerativelyrevisesitsharnessbyanalyzingexecutiontrajectoriesandpriorharnesshistory.EMHOoptimizesbeyondskillsorrecoveryprompts,modifyinghowtheagentmonitorsprogress,usesvisiontools,groundsobservations,andrespondstofailures.Tosupportmultiplesubtaskswithasingleharness,weintroduceEMHO-Merge,whichaddressestrade-offsinjointlyoptimizingasinglesharedharnessacrosssubtasksbyusingepisode-levelgainsandlossestoguideevidence-supportedrefinementofwhenandhowrevisedbehaviorsareapplied.WeevaluateEMHOonEmbodiedBenchacrossnavigationandmanipulationtasks,andEMHOconsistentlyimprovestasksuccessforbothQwen9Band27Bmodels.QualitativeanalysisshowsthatEMHOgoesbeyondrecoveringfromfailuresandunproductiveactionstoreshapehowtheembodiedagentinterpretsandinteractswithitsenvironment.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2610\.08432

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.08432 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.08432 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.08432 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Harness^2: Recursive Agent Harnessing for an Open World

Hugging Face Daily Papers

Harness² 提出了一种即插即用的递归智能体框架（Recursive Agent Harnessing），通过任务级与框架级两层递归改进，在无 ground-truth 验证器的开放世界场景中自动优化智能体执行框架，并在多个专业基准上显著提升了 GLM-5 与 Gemini 3.5 Flash 的表现。

Self-Evolving Agent Harness

Hugging Face Daily Papers

提出一个自我进化代理框架（Harness RSI），在保持模型权重固定的情况下，通过反馈驱动的修订与进化优化来持续改进代理的软件脚手架（提示、记忆、工作流和可执行组件），并借助持续 PAC 学习给出泛化与保留的理论保证。

HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry

Hugging Face Daily Papers

HarnessX is a foundry for composable, adaptive, and evolvable AI agent harnesses that uses compositional primitives and trace-driven evolution to improve agent performance. Across five benchmarks, it achieves an average gain of +14.5% (up to +44.0%), demonstrating that runtime interface evolution is a complementary lever to model scaling.