[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82491-en":3,"doc-seo-82491-105":29,"detail-sidebar-cat-0-en-105":83},{"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},82491,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253",8,"Research & Report","ASPIRE Agentic Skills Discovery for Robotics","Traditional robot programming is difficult because it must coordinate multimodal perception, complex contact dynamics, and failure-prone execution across diverse environments. Aspire (Agentic Skill Programming through Iterative Robot Exploration) is a continual learning system that autonomously writes and refines robot control programs in a code-as-policy setting and compounds experience into a reusable skill library. It uses a closed-loop robot execution engine with fine-grained traces, a continually expanding skill library, and evolutionary search to iteratively debug diverse task sequences. Aspire improves manipulation performance by up to 77%, supports zero-shot long-horizon success, and provides evidence of simulation-to-real transfer that reduces real-robot programming effort.","arXiv :2607 .00272v1 [ cs .RO] 30 Jun 2026  \nASPIRE: Agentic /Skills Discovery for Robotics  \nRunyu Lu 1 2 * †, Yubo Wu 1 3 * , Ethan Kou 1 4 *  \nLetian Fu1 4 , Wenli Xiao1 5 , Ajay Mandlekar 1 , Yinzhen Xu 1 Guanya Shi5 , Ken Goldberg4 , Ang Chen2 , Mosharaf Chowdhury2 Yuke Zhu1 †, Linxi “Jim” Fan 1 †, Guanzhi Wang1 †  \n1 NVIDIA, 2 UMich, 3 UIUC, 4 UC Berkeley, 5 CMU  \n* Equal contribution, † Project leads [https://research.nvidia.com/labs/gear/aspire/](https://research.nvidia.com/labs/gear/aspire/)  \nAbstract:  \nTraditional robot programming is notoriously challenging: it requires orchestrating multimodal perception, managing complex physical contact dynamics, and handling diverse environment configurations and execution failures. We introduce Aspire (Agentic Skill Programming through Iterative Robot Exploration), a continual learning system for robotics that autonomously writes and refines robot control programs ina code-as-policy paradigm while compounding experience into a reusable skill library. Aspire enables automated discovery of reusable skills that persist across multiple tasks, simulation and real-world settings, and different embodiments. Rather than relying on fixed, human-engineered pipelines, Aspire operates inan open-ended learning loop, consisting of three key components: (1) a closed-loop robot execution engine that exposes fine-grained multimodal traces (e.g. , perception overlays, grasp candidates, motion trajectories, and collision feedback), enabling the agent to autonomously diagnose failures, synthesize repairs, and validate outcomes; (2) a continually expanding skill library that distills validated fixes into reusable, transferable robotic knowledge; and (3) an evolutionary search procedure that generates diverse task sequences and control programs, systematically debugging them to explore beyond single-trajectory refinement. As Aspire encounters more tasks, its growing skill library enables increasingly rapid adaptation. Consequently, Aspire surpasses prior methods by up to 77% on manipulation tasks under perturbation (LIBERO-Pro), 72% on Robosuite’s bimanual handover task, and up to 32% on long-horizon household tasks (BEHAVIOR-1K) . The accumulated skill library further enables strong zero-shot generalization: on representative unseen long-horizon tasks (LIBERO-Pro Long), Aspire achieves 31% success, substantially outperforming the 4% success rate of prior methods despite their heavy reliance on test-time reasoning and retries. Finally, skills discovered in simulation provide initial evidence of sim-to-real transfer, substantially reducing real-robot programming effort despite different embodiments and robot APIs.  \n1. Introduction  \nRecent progress in software engineering agents demonstrates that language models can autonomously inspect execution traces, localize failures, revise implementations, and improve through repeated interaction with execution environments [Anthropic, 2025, OpenAI, 2025, anomalyco, 2025, Wanget al., 2025, Yang et al., 2024] . In robotics, this paradigm has inspired code-as-policy systems that compose perception modules, planning APIs, and control primitives into executable robot programs [Liang et al., 2023, Singh et al., 2023, Ahn et al., 2022, Huang et al., 2023, Mu et al. , 2024, Fu et al., 2026] . Because robot behaviors are represented explicitly as programs, they can in principle be inspected, edited, debugged, and refined through interaction feedback.  \nHowever, existing robotic coding agents remain fundamentally limited by naive execution environments that provide only coarse task-level feedback. Debugging robot programs is intrinsically challenging because failures can arise from many interacting components, including multimodal perception, motion planning, grasp generation, contact dynamics, and long-horizon task coordination. A failed rollout may indicate that the task did not succeed, but not whether the root cause is incorrect perception, an unstable grasp, a ","cbCaioozZq8vb3ty","https://ap.wps.com/l/cbCaioozZq8vb3ty","pdf",5769112,1,43,"English","en",105,"# Introduction\n## Robot Execution and Debugging\n## Multimodal Traces and Failure Attribution\n## Continual Skill Library\n## Evolutionary Search and Iterative Refinement\n## Performance on Manipulation and Long-Horizon Tasks","[{\"question\":\"What performance gains does Aspire report compared with prior methods?\",\"answer\":\"Aspire uses skills discovered in simulation as evidence of sim-to-real transfer, reducing real-robot programming effort even across different embodiments and robot APIs.\"}]",1784180891,108,{"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":78,"head_meta":80,"extra_data":82,"updated_unix":27},"aspire-agentic-skills-discovery-for-robotics","",{"@graph":35,"@context":77},[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/aspire-agentic-skills-discovery-for-robotics/82491/",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],{"name":72,"@type":73,"acceptedAnswer":74},"What performance gains does Aspire report compared with prior methods?","Question",{"text":75,"@type":76},"Aspire uses skills discovered in simulation as evidence of sim-to-real transfer, reducing real-robot programming effort even across different embodiments and robot APIs.","Answer","https://schema.org",{"og:url":51,"og:type":79,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":81,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,127],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":45,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":45,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":45,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":45,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":98,"slug":130},19,"General","general"]