Embodied agents built on foundation models rely on an execution harness to organize observations, guide actions, and incorporate execution feedback into subsequent decisions. Failures can arise not only from limited model capabilities, but also from how the harness presents evidence and guides its use. These model-external mechanisms provide an adaptation target without updating model parameters, but task-specific interaction experience can be costly to collect. Task-level outcomes alone do not reveal whether relevant evidence was missing from the model input or was available but inadequately used. Moreover, these two aspects are coupled: effective action guidance may require evidence that the current context omits, while exposing that evidence alone does not ensure an appropriate response. We introduce EnactOpt, which uses limited execution feedback to jointly evolve reusable textual skills and context-construction code while keeping the underlying models and runtime fixed. It diagnoses adjacent decisions by relating action feedback to the actual model input and subsequent action. Structured episode summaries guide joint revisions through prompt-level edit operators, and candidate harnesses undergo compatibility checks and validation-based retention. Across VLABench, ALFWorld, and Embodied Agent Interface (EAI), EnactOpt improves task success by approximately 10-27 percentage points over the initial harnesses and outperforms the evaluated GEPA, TextGrad, and Trace2Skill baselines. These gains extend to task conditions not used for harness evolution or candidate selection. The results support a complementary route to embodied adaptation: turning limited execution experience into reusable behavioral improvements by jointly refining how evidence is presented and acted upon.
UAVs Meet Embodied Intelligence: Bridging Human Intents and Flying Dynamics Via Harnessing Physical-Digital AI Agents
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Beihang University(北京航空航天大学);Shanxi Datong University(山西大同大学);Johns Hopkins University(约翰斯·霍普金斯大学);University of Sanya(三亚学院);Wenzhou-Kean University(温州肯恩大学);Macau University of Science and Technology(澳门科技大学);KOKONI 3D, Moxin Technology(魔芯科技KOKONI 3D);University of Science and Technology of China(中国科学技术大学)
Guava: Distilling Frontier VLMs into a Compact Agent through a Robotic Manipulation Harness
University of Maryland College Park(马里兰大学帕克分校);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Waterloo(滑铁卢大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);University of Pennsylvania(宾夕法尼亚大学);Amazon FAR(亚马逊 FAR)
Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution
School of Software, Harbin Institute of Technology(哈尔滨工业大学软件学院);School of Computer Science and Technology, Harbin Institute of Technology(哈尔滨工业大学计算机科学与技术学院);School of Mathematical and Computer Sciences, Heriot-Watt University, Malaysia Campus(赫瑞-沃德大学马来西亚校区数学与计算机科学学院);School of Future Science and Engineering, Soochow University(苏州大学未来科学与工程学院);Fraunhofer Institute for Applied Information Technology(弗劳恩霍夫应用信息技术研究所)
HarnessWAM: Bridging Prediction and Deliberation in World Action Models
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Yinwang Intelligent Technology Co., Ltd.(银湾智能科技有限公司);Beijing Institute of Technology(北京理工大学);Wuhan AI Research(武汉人工智能研究院)
Embodied Agents Take Control: Minimal-Interface Zero-Shot Agents Rival Industrial-Scale Policies in Vision-and-Language Navigation
Australian Institute for Machine Learning(澳大利亚机器学习研究所);Adelaide University(阿德莱德大学);Responsible AI Research Centre(负责任人工智能研究中心);CSIRO Data61(联邦科学与工业研究组织数据61中心);The University of Queensland(昆士兰大学)
ACE: Agentic Control for Embodied Manipulation via Zero-shot Workflow Reasoning
Department of Computer Science, Tsinghua University(清华大学计算机科学系);National College for Excellent Engineers, Beihang University(北京航空航天大学卓越工程师学院);Wuxi Dexteroushands Robotic Technology Co.(无锡灵犀机器人技术有限公司)
RegenHarness: A Robot Agent Harness with Evidence-Gated Recursive Self-Improvement
AI Lab, Country Garden Services Group(碧桂园服务集团AI实验室);School of Mechanical Science and Engineering, Huazhong University of Science and Technology(华中科技大学机械科学与工程学院);Omni AI
Building Cooperative Embodied Agents Modularly with Large Language Models
University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);Tsinghua University(清华大学);Shanghai Jiao Tong University(上海交通大学);MIT(麻省理工学院);MIT-IBM Watson AI Lab(麻省理工学院-IBM沃森人工智能实验室)