[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84965-en":3,"doc-seo-84965-105":30,"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},84965,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","PriGo Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation","Imitation learning enables diffusion and flow policies to generate complex visuomotor behaviors from demonstrations, yet they often generalize poorly under task and environment distribution shifts. PriGo introduces a test-time adaptive framework that uses primitive guidance to align inferred actions with underlying manipulation intent rather than superficial action correlations. A lightweight PANet predicts primitive distributions from observations, and differentiable guidance refines diffusion and flow actions during inference. Experiments on LIBERO, CALVIN, SIMPLER, and real robots show improved robustness, long-horizon execution, and cross-policy generalization.","arXiv :2607 .07076v 1 [ cs .RO] 8 Jul 2026  \nPriGo: Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation  \nZezeng Li 1 , Enda Xiang2 , Thuy Tran 1 , Di Huang2 , Momath Thiam 1 , Liming Chen 1  \n1´Ecole Centrale de Lyon, France 2Beihang University, China  \nAbstract: Imitation learning has enabled remarkable progress in robotic manipulation, especially with diffusion and flow-based policies that generate complex visuomotor behaviors directly from demonstrations. Yet, despite their strong performance, these policies often fail to generalize across tasks and environments. A key reason is that existing policies tend to imitate superficial action correlations rather than the underlying intent. Inspired by the compositional structure of human behaviors, we propose PriGo, a primitive-guided test-time adaptive framework for robust robotic manipulation. PriGo introduces PANet, a lightweight primitive prediction module that infers primitive distributions directly from observations. We further propose a differentiable primitive guidance mechanism that refines generated actions during inference, steering trajectories toward semantically consistent behaviors. Unlike prior primitive-conditioned approaches, PriGo operates entirely at test time and can be seamlessly integrated into pretrained diffusion and flow policies without retraining. Extensive experiments on LIBERO, CALVIN, SIMPLER, and real-world robotic tasks demonstrate that PriGo consistently improves robustness, long-horizon execution, and generalization ability across both diffusion and flow-based policies. Codes are available on PriGo.  \n1 Introduction  \nImitation learning (IL) has become a dominant paradigm for robotic manipulation, enabling policies to acquire complex visuomotor behaviors directly from expert demonstrations without manually designed reward functions. Recent diffusion and flow-based policies have further improved action generation quality by modeling multi-modal action distributions and leveraging large-scale visionlanguage representations. Despite these advances, existing policies often remain brittle under distribution shifts, including variations in object, lighting, distractors, and unseen task [1, 2] .  \nA key limitation is that current policies primarily learn correlations between observations and lowlevel actions, rather than the underlying structural intent of manipulation behaviors. Consequently, generated actions may locally resemble expert demonstrations while failing to preserve the intended motion structure required for successful task completion. As shown in Fig. 1.a, when opening a door, the policy incorrectly pulls before rotating the key, or generates unstable grasping motions under environmental perturbations. Such failures become particularly severe in long-horizon manipulation, where small local errors accumulate across multiple subtasks. To improve robustness and generalization, an important direction is to incorporate structured action priors into policy generation. Human manipulation behaviors naturally exhibit compositional structure, where complex tasks are composed of a small number of reusable motion primitives such as grasping, pushing, pulling, and rotation. Rather than treating actions as unconstrained continuous trajectories, these primitives provide a compact structural prior that constrains policies toward semantically consistent behaviors.  \nRecent works [3, 4] have sought to disentangle primitives into discrete types with associated parameters, capturing both categorical abstractions and low-level action prediction. However, they limit the primitive set to basic actions, which restricts their applicability to more complex tasks. Furthermore, primitive taxonomy consisting of eight manipulation primitives, providing a balance between structural expressiveness and cross-task generalization.  \nthese methods treat primitives as additional input rather than enforcing them as mandatory constrain","cbCaijXoEHR7BWBI","https://ap.wps.com/l/cbCaijXoEHR7BWBI","pdf",14890404,3,1,15,"English","en",105,"# Introduction\n## Structured vs. unstructured primitive actions\n## Contributions","[{\"question\":\"What problem does PriGo address in diffusion and flow imitation policies?\",\"answer\":\"It targets the brittleness of imitation policies under distribution shifts, where generated actions may match superficial correlations but fail to preserve the structural intent needed for successful long-horizon manipulation.\"},{\"question\":\"How does PriGo obtain primitive information during inference?\",\"answer\":\"PriGo uses PANet, a lightweight primitive prediction module that infers primitive distributions from observations (and language instructions as described), without requiring policy retraining.\"},{\"question\":\"How is primitive guidance applied to diffusion and flow policies?\",\"answer\":\"PriGo incorporates a differentiable primitive guidance mechanism that refines generated actions during inference using gradients from primitive consistency objectives, steering trajectories toward semantically consistent behaviors.\"}]",1784199752,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"prigo-test-time-primitive-guidance-to-diffusion-and-flow-policies-for-adaptive-robotic-manipulation","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/prigo-test-time-primitive-guidance-to-diffusion-and-flow-policies-for-adaptive-robotic-manipulation/84965/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-23","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 PriGo address in diffusion and flow imitation policies?","Question",{"text":75,"@type":76},"It targets the brittleness of imitation policies under distribution shifts, where generated actions may match superficial correlations but fail to preserve the structural intent needed for successful long-horizon manipulation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does PriGo obtain primitive information during inference?",{"text":80,"@type":76},"PriGo uses PANet, a lightweight primitive prediction module that infers primitive distributions from observations (and language instructions as described), without requiring policy retraining.",{"name":82,"@type":73,"acceptedAnswer":83},"How is primitive guidance applied to diffusion and flow policies?",{"text":84,"@type":76},"PriGo incorporates a differentiable primitive guidance mechanism that refines generated actions during inference using gradients from primitive consistency objectives, steering trajectories toward semantically consistent behaviors.","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":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]