LDP: An Identity-Aware Protocol for Multi-Agent LLM Systems

LDP: An Identity-Aware Protocol for Multi-Agent LLM Systems | 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Research Article LDP: An Identity-Aware Protocol for Multi-Agent LLM Systems Sunil Prakash This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9121599/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract As multi-agent AI systems scale to production, the protocols connecting them constrain their capabilities. Current protocols such as Google's A2A and Anthropic's MCP omit model-level metadata, preventing quality-aware routing, efficient communication, and governance. We present the LLM Delegate Protocol (LDP), which introduces five AI-native primitives: rich delegate identity cards, progressive payload negotiation, governed sessions, structured provenance, and trust domains. We implement LDP as a plugin adapter for the JamJet agent runtime and evaluate it against A2A and random baselines. Identity-aware routing achieves 12x lower latency on easy tasks; semantic frame payloads reduce token count by 37 percent with no quality loss; governed sessions eliminate 39 percent token overhead; and noisy provenance degrades quality below the no-provenance baseline, showing that confidence metadata is harmful without verification. Trust domain and fallback analyses demonstrate architectural advantages in security and resilience. This paper contributes a protocol design, reference implementation, and initial evidence that AI-native protocol primitives enable more efficient and governable multi-agent delegation. agent protocols multi-agent systems LLM delegation payload negotiation AI interoperability trust domains Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-9121599","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":608351862,"identity":"c208d195-a746-4df0-b186-d5c84a73a110","order_by":0,"name":"Sunil Prakash","email":"data:image/png;base64,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","orcid":"","institution":"Indian School of Business","correspondingAuthor":true,"prefix":"","firstName":"Sunil","middleName":"","lastName":"Prakash","suffix":""}],"badges":[],"createdAt":"2026-03-14 10:08:59","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9121599/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9121599/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105034732,"identity":"d5f815cc-90c8-428d-b445-278d83aef971","added_by":"auto","created_at":"2026-03-20 07:23:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":385497,"visible":true,"origin":"","legend":"","description":"","filename":"ldpjaamassubmission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9121599/v1_covered_f28e2e60-2657-487f-b7cd-95752e859227.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"LDP: An Identity-Aware Protocol for Multi-Agent LLM Systems","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"agent protocols, multi-agent systems, LLM delegation, payload negotiation, AI interoperability, trust domains","lastPublishedDoi":"10.21203/rs.3.rs-9121599/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9121599/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"As multi-agent AI systems scale to production, the protocols connecting them constrain their capabilities. Current protocols such as Google's A2A and Anthropic's MCP omit model-level metadata, preventing quality-aware routing, efficient communication, and governance. We present the LLM Delegate Protocol (LDP), which introduces five AI-native primitives: rich delegate identity cards, progressive payload negotiation, governed sessions, structured provenance, and trust domains. We implement LDP as a plugin adapter for the JamJet agent runtime and evaluate it against A2A and random baselines. Identity-aware routing achieves 12x lower latency on easy tasks; semantic frame payloads reduce token count by 37 percent with no quality loss; governed sessions eliminate 39 percent token overhead; and noisy provenance degrades quality below the no-provenance baseline, showing that confidence metadata is harmful without verification. Trust domain and fallback analyses demonstrate architectural advantages in security and resilience. This paper contributes a protocol design, reference implementation, and initial evidence that AI-native protocol primitives enable more efficient and governable multi-agent delegation.","manuscriptTitle":"LDP: An Identity-Aware Protocol for Multi-Agent LLM Systems","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-19 10:18:36","doi":"10.21203/rs.3.rs-9121599/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"d0126463-8a6f-4e4f-8b90-4f068e49c35b","owner":[],"postedDate":"March 19th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-19T10:18:36+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-19 10:18:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9121599","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9121599","identity":"rs-9121599","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}