RoDA: A Role-Playing Dual-Agent Framework to Drive Nursing Robots in Bimanual Coordination Tasks

RoDA: A Role-Playing Dual-Agent Framework to Drive Nursing Robots in Bimanual Coordination Tasks | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article RoDA: A Role-Playing Dual-Agent Framework to Drive Nursing Robots in Bimanual Coordination Tasks Zhendong Zhao, Yang Li, Jiexin Xie, Tonghui Zhang, Shijie Guo This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7368845/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 9 You are reading this latest preprint version Abstract Effective bimanual collaboration represents a significant research objective for Large Language Model (LLM)-driven nursing robots. However, current approaches are constrained by critical limitations: the single-thread LLM task planner (ST-Planner) lacks co-scheduling, while the conventional multi-agent framework (DABICO) suffers from inefficient information interaction between agents, consequently compromising performance in bimanual collaboration tasks. To overcome these limitations, this study introduces Role-playing Dual Agents (RoDA), a novel dual-agent collaboration framework augmented by LLM Role-Playing. This framework implements the nursing robot as an LLM-based dual-agent system wherein each agent assumes the role of either the left or right arm. Through meticulously crafted contextual prompts explicitly defining specific identity attributes and conversational protocols for each limb, these agents facilitate high-quality collaborative dialogue reflective of their designated roles. Evaluation of RoDA was conducted through four MuJoCo simulation scenarios encompassing all four categories of bimanual collaboration, diverse task sequences, and different degrees of workspace overlap. The experimental results demonstrate that the role-playing mechanism enhances dialogue normalization, accuracy, and information richness. This high-quality interaction enables superior task planning performance, with RoDA surpassing both the ST-Planner and the baseline DABICO framework. Specifically, RoDA achieved a \((100%)\) success rate across all scenarios, exhibiting an average performance improvement of \((16.3%)\) in the Step metric and \((70.2%)\) in the Restep metric relative to DABICO. Furthermore, enhancement of performance is achieved without the requirement for LLM fine-tuning, offering advantages including flexibility, immediacy, and low development cost. Finally, RoDA was demonstrated through practical experiments on a dual-arm nursing robot. nursing robot dual-agent system LLM role-playing dialogic co-scheduling bimanual coordination tasks Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 18 May, 2026 Reviews received at journal 10 May, 2026 Reviewers agreed at journal 10 May, 2026 Reviewers agreed at journal 05 May, 2026 Reviewers agreed at journal 10 Apr, 2026 Reviewers invited by journal 13 Sep, 2025 Editor assigned by journal 19 Aug, 2025 Submission checks completed at journal 19 Aug, 2025 First submitted to journal 13 Aug, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7368845","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":515838961,"identity":"b021a86d-48d5-4af7-94b9-8c00392d2ac8","order_by":0,"name":"Zhendong Zhao","email":"data:image/png;base64,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","orcid":"","institution":"Hebei University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Zhendong","middleName":"","lastName":"Zhao","suffix":""},{"id":515838962,"identity":"d13190b0-22a5-4eb8-b79c-21b948b7fcbf","order_by":1,"name":"Yang Li","email":"","orcid":"","institution":"Hebei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Yang","middleName":"","lastName":"Li","suffix":""},{"id":515838963,"identity":"f350297d-e377-4c24-9abb-43bb2c47c8ba","order_by":2,"name":"Jiexin Xie","email":"","orcid":"","institution":"Guilin University of Electronic Technology","correspondingAuthor":false,"prefix":"","firstName":"Jiexin","middleName":"","lastName":"Xie","suffix":""},{"id":515838964,"identity":"5274518d-ce3b-4f59-a5b1-47f7fda0994b","order_by":3,"name":"Tonghui Zhang","email":"","orcid":"","institution":"Hebei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Tonghui","middleName":"","lastName":"Zhang","suffix":""},{"id":515838965,"identity":"3110c3dc-e4ac-44a8-968e-855d22888703","order_by":4,"name":"Shijie Guo","email":"","orcid":"","institution":"Hebei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Shijie","middleName":"","lastName":"Guo","suffix":""}],"badges":[],"createdAt":"2025-08-14 01:53:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7368845/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7368845/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91710518,"identity":"fbbfa113-1795-4c09-a930-ec5f49ffef4b","added_by":"auto","created_at":"2025-09-19 12:27:31","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3494559,"visible":true,"origin":"","legend":"","description":"","filename":"RoDA.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7368845/v1_covered_b6dab164-81b7-4317-8673-e0ba0972bd47.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eRoDA: A Role-Playing Dual-Agent Framework to Drive Nursing Robots in Bimanual Coordination Tasks\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"journal-of-intelligent-and-robotic-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Journal of Intelligent \u0026 Robotic Systems](https://link.springer.com/journal/10846)","snPcode":"10846","submissionUrl":"https://submission.springernature.com/new-submission/10846/3","title":"Journal of Intelligent \u0026 Robotic Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"nursing robot, dual-agent system, LLM role-playing, dialogic co-scheduling, bimanual coordination tasks","lastPublishedDoi":"10.21203/rs.3.rs-7368845/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7368845/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eEffective bimanual collaboration represents a significant research objective for Large Language Model (LLM)-driven nursing robots. However, current approaches are constrained by critical limitations: the single-thread LLM task planner (ST-Planner) lacks co-scheduling, while the conventional multi-agent framework (DABICO) suffers from inefficient information interaction between agents, consequently compromising performance in bimanual collaboration tasks. To overcome these limitations, this study introduces Role-playing Dual Agents (RoDA), a novel dual-agent collaboration framework augmented by LLM Role-Playing. This framework implements the nursing robot as an LLM-based dual-agent system wherein each agent assumes the role of either the left or right arm. Through meticulously crafted contextual prompts explicitly defining specific identity attributes and conversational protocols for each limb, these agents facilitate high-quality collaborative dialogue reflective of their designated roles. Evaluation of RoDA was conducted through four MuJoCo simulation scenarios encompassing all four categories of bimanual collaboration, diverse task sequences, and different degrees of workspace overlap. The experimental results demonstrate that the role-playing mechanism enhances dialogue normalization, accuracy, and information richness. This high-quality interaction enables superior task planning performance, with RoDA surpassing both the ST-Planner and the baseline DABICO framework. Specifically, RoDA achieved a \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\((\u0026lt;Emphasis Type=\u0026quot;Bold\u0026quot;\u0026gt;100%\u0026lt;/Emphasis\u0026gt;)\\)\u003c/span\u003e\u003c/span\u003e success rate across all scenarios, exhibiting an average performance improvement of \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\((\u0026lt;Emphasis Type=\u0026quot;Bold\u0026quot;\u0026gt;16.3%\u0026lt;/Emphasis\u0026gt;)\\)\u003c/span\u003e\u003c/span\u003e in the Step metric and \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\((\u0026lt;Emphasis Type=\u0026quot;Bold\u0026quot;\u0026gt;70.2%\u0026lt;/Emphasis\u0026gt;)\\)\u003c/span\u003e\u003c/span\u003e in the Restep metric relative to DABICO. Furthermore, enhancement of performance is achieved without the requirement for LLM fine-tuning, offering advantages including flexibility, immediacy, and low development cost. Finally, RoDA was demonstrated through practical experiments on a dual-arm nursing robot. \u003c/p\u003e","manuscriptTitle":"RoDA: A Role-Playing Dual-Agent Framework to Drive Nursing Robots in Bimanual Coordination Tasks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-19 12:03:25","doi":"10.21203/rs.3.rs-7368845/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-18T15:11:49+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-10T23:25:28+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"239626466657371900286780060390234725619","date":"2026-05-10T22:04:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"78385573558233363389052344060903289061","date":"2026-05-05T16:33:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"238663810857711414396724565978502310756","date":"2026-04-10T04:21:40+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-13T22:25:16+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-19T06:26:14+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-19T06:22:35+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Intelligent \u0026 Robotic Systems","date":"2025-08-14T01:51:35+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-intelligent-and-robotic-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Journal of Intelligent \u0026 Robotic Systems](https://link.springer.com/journal/10846)","snPcode":"10846","submissionUrl":"https://submission.springernature.com/new-submission/10846/3","title":"Journal of Intelligent \u0026 Robotic Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"22868463-b652-4f95-87b3-a88f65509757","owner":[],"postedDate":"September 19th, 2025","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-18T15:11:49+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-10T23:25:28+00:00","index":36,"fulltext":""},{"type":"reviewerAgreed","content":"239626466657371900286780060390234725619","date":"2026-05-10T22:04:26+00:00","index":35,"fulltext":""},{"type":"reviewerAgreed","content":"78385573558233363389052344060903289061","date":"2026-05-05T16:33:00+00:00","index":33,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-05-18T15:24:31+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-19 12:03:25","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7368845","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7368845","identity":"rs-7368845","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}