[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82791-en":3,"doc-seo-82791-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82791,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","ACE: Agentic Control for Embodied Manipulation via Zero-shot Workflow Reasoning","Open-ended tabletop manipulation requires agents to understand natural language while adapting to dynamic environments and execution failures. ACE (Agentic Control for Embodied manipulation) introduces a zero-shot workflow reasoning framework for tabletop pick-and-place driven by natural language. Instead of direct low-level action mapping, ACE combines agentic workflow decomposition with reusable robot-executable skills: a mask-mediated visual grounding interface and a pick-and-place primitive. Active sub-goals are grounded, tracked, verified, and passed to a task-agnostic policy. Closed-loop post-execution verification enables advance, retry, repair, or replan based on outcomes. Evaluation on complex long-horizon tasks shows task-level zero-shot generalization without task-specific retraining, including 50% success for equation formation and 70% for constraint retrieval.","arXiv :2607 .04 162v 1 [ cs .RO] 5 Jul 2026  \nACE: Agentic Control for Embodied Manipulation via Zero-shot Workflow Reasoning  \nIok Tong Lei 1,†, QianZhi Li2,†, Ying Jie Yap 1 , Yujie Zhang4 , Rui Zhong2 , Haichao Gui2,* ,  \nXiaolong Liu3,* , Zhidong Deng 1,*  \n1Department of Computer Science, Tsinghua University, China  \n2National College for Excellent Engineers, Beihang University, China  \n3Wuxi Dexteroushands Robotic Technology Co.  \n4Independent Researcher  \n†These authors contributed equally to this work.  \n* Corresponding authors.  \nAbstract: Open-ended tabletop manipulation requires agents to not only understand natural language but also adapt to dynamic environments and execution failures. We present ACE (Agentic Control for Embodied manipulation), a zero-shot workflow reasoning framework for tabletop pick-and-place from natural language.  \nRather than relying on direct low-level action mapping, ACE combines agentic workflow reasoning with two robot-facing executable skills: a visual grounding interface and a reusable pick-and-place primitive. To bridge semantic reasoning and physical control, the active sub-goal is grounded into a mask-mediated vision-action interface. This unified mask specifies the target object and destination, is tracked over time, exposed for human verification, and ultimately passed to a task-agnostic downstream policy for execution. Crucially, ACE operates ina closed loop supported by a multi-timescale memory. After an action is executed, the system automatically verifies whether the intended sub-goal succeeded, using the outcome to advance, retry, repair, or replan. This enables online adaptation to user corrections, scene changes, and physical failures. We evaluate ACE on logically complex, long-horizon tasks, including zero-shot multi-step equation formation with number cubes and constraint-based object retrieval. ACE demonstrates task-level zero-shot generalization on novel semantic constraints and randomized tabletop scenes without task-specific retraining. Specifically, while standard end-to-end baselines struggle to complete these logically demanding tasks, ACE achieves a 50% success rate in equation formation and a 70% success rate in constraint retrieval. This contrast demonstrates that explicit workflow reasoning and mask-mediated control offer a robust, practical route toward adaptable robotic manipulation.  \nKeywords: Embodied reasoning, Robot manipulation, Zero-shot planning  \n1 Introduction  \nNatural language provides an intuitive interface for open-ended robotic control, allowing users to specify high-level goals and refine intent dynamically. However, this flexibility makes execution inherently difficult. Instructions are often underspecified, and task constraints may emerge only after execution begins [1, 2, 3] . This challenge is particularly visible in tabletop pick-and-place. While a basic robotic primitive, executing open-ended tasks—such as forming equations from number cubes based on abstract constraints—requires more than recognizing objects and executing grasps. Traditional manipulation systems often rely on task-specific policies or libraries of fixed rules [4, 5], which struggle to generalize when goals vary significantly across episodes. To succeed, a system  \n(A) Vision-Action Model (VA)  \nVA Model  \nLow Level Actions  \nLacks Instruction Following Capability  \n(B) Vision-Language-Action Model (VLA)  \nLacks Robust Zero-Shot Reasoning for Complex, Long-Horizon Task  \n(C) Proposed ACE Method  \nEnables Logically Complex, Long-Horizon Reasoning and Planning  \nFigure 1: Comparison of robotic manipulation paradigms. (A) Vision-Action (VA) Models execute low-level actions based on visual observations. (B) Vision-Language-Action (VLA) Models can condition actions on language, but direct language-to-action mapping may struggle with strict compositional reasoning, long-horizon sequencing, and recovery under limited task data. (C) Our Proposed ACE Framework decouples reasoning ","cbCaiqvLbC4aXFPw","https://ap.wps.com/l/cbCaiqvLbC4aXFPw","pdf",1204735,1,12,"English","en",105,"# Abstract\n# Introduction\n## Figure 1: Comparison of robotic manipulation paradigms\n## ACE framework overview","[{\"question\":\"What problem does ACE address in tabletop pick-and-place?\",\"answer\":\"ACE targets open-ended manipulation where natural-language instructions are under-specified and where execution may fail due to semantic or physical issues. It aims to maintain reliable performance without task-specific retraining.\"},{\"question\":\"How does ACE connect workflow reasoning to robot control?\",\"answer\":\"ACE decouples high-level reasoning from low-level physical execution using a mask-mediated vision-action interface. The agent produces semantic pick-and-place masks via grounding skills, which condition a reusable vision-action policy for execution.\"},{\"question\":\"How does ACE handle failures or user corrections during execution?\",\"answer\":\"After each action, ACE verifies whether the intended sub-goal succeeded. The verification outcome drives online adaptation, including advancing, retrying, repairing, or replanning based on changes in the scene, user feedback, or physical failures.\"}]",1784182961,30,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"ace-agentic-control-for-embodied-manipulation-via-zero-shot-workflow-reasoning","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/ace-agentic-control-for-embodied-manipulation-via-zero-shot-workflow-reasoning/82791/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does ACE address in tabletop pick-and-place?","Question",{"text":75,"@type":76},"ACE targets open-ended manipulation where natural-language instructions are under-specified and where execution may fail due to semantic or physical issues. It aims to maintain reliable performance without task-specific retraining.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does ACE connect workflow reasoning to robot control?",{"text":80,"@type":76},"ACE decouples high-level reasoning from low-level physical execution using a mask-mediated vision-action interface. The agent produces semantic pick-and-place masks via grounding skills, which condition a reusable vision-action policy for execution.",{"name":82,"@type":73,"acceptedAnswer":83},"How does ACE handle failures or user corrections during execution?",{"text":84,"@type":76},"After each action, ACE verifies whether the intended sub-goal succeeded. The verification outcome drives online adaptation, including advancing, retrying, repairing, or replanning based on changes in the scene, user feedback, or physical failures.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":28,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]