LinkPulse: A Hybrid Retrieval-Augmented Generation Platform for Autonomous Multi-Source Knowledge Synthesis

LinkPulse: A Hybrid Retrieval-Augmented Generation Platform for Autonomous Multi-Source Knowledge Synthesis | 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 LinkPulse: A Hybrid Retrieval-Augmented Generation Platform for Autonomous Multi-Source Knowledge Synthesis Tapasvi Panchagnula, Shivani Reddy Alumalla, Indirala Surya, K. Divyasri, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9186511/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 Retrieval-Augmented Generation (RAG) has emerged as a principled approach to grounding large language model (LLM) responses in external knowledge, yet deployed systems face three persistent limitations: (1) single-modality retrieval that degrades on semantically diverse queries; (2) fragmented knowledge sources that cannot unify static corpora with real-time web signals; and (3) monolithic architectures that resist component-level optimisation and scaling. We propose LinkPulse, an autonomous knowledge-synthesis platform that addresses these limitations through three technical contributions. First, the Tri-Modal Fusion Retriever (tmfr) dynamically weights dense vector similarity, sparse BM25 keyword matching, and live web-search signals via a lightweight learned gating network. Second, the Multi-Agent Ingestion Pipeline (maip) abstracts heterogeneous sources—web pages, GitHub repositories, PDFs, and multimedia—into a unified vector-indexed knowledge store with source-aware provenance tracking. Third, the Adaptive Context Window (acw) combines cross-encoder re-ranking with extractive sentence compression to reduce context dilution before generation. We evaluate LinkPulse on LinkPulse-Bench, a curated multi-domain benchmark of 150 queries spanning 1,000+ indexed documents across three content categories. On our benchmark, LinkPulse achieves an F1 score of 97.1, outperforming TF-IDF (+13.3 points), vector-only RAG (+3.4 points), and Self-RAG (+1.2 points), while reducing mean response latency to 230 ms and an observed hallucination rate of 3.2% on our test set. Ablation experiments confirm that each component contributes independently to performance. We release LinkPulse-Bench and all code to support reproducibility. Artificial Intelligence and Machine Learning Retrieval-Augmented Generation Hybrid Search Multi-Agent Systems Knowledge Synthesis Large Language Models Information Retrieval Full Text Additional Declarations The authors declare no competing interests. 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-9186511","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":609905031,"identity":"054adc11-ed63-4b7d-8c92-5be73a74091b","order_by":0,"name":"Tapasvi Panchagnula","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/UlEQVRIiWNgGAWjYPACiXr2ZhBdAcTMzA141fJAtSTwHAbRZ0BaGInSwpDAcwBIMraB2AS02LOfPfjxZ5tFHg8778OHP+fVRvO3A7X8qNiG2xaevGRp3jaJYh5mdmNj3m3Hc2ccZmxg7DlzG4/DcgykGc5IMO5nZmOTZtx2LLcBqIWZsQ2PFv43xj9/ALX0MLOx//w551jufIJaJHLMJHgqJBKBWtgYeBtqcjcQ1HLjXZo1UIsxDzMbszTPsQO5G4FaDuLzC3t/7uGbPwzq5Hj4jzF+/FFTlzvv/OGDD35U4NaCiBkIAEcowwE86jG01OFXPApGwSgYBSMSAAABjFHlUsdu6QAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0009-0005-0114-1432","institution":"Sreenidhi Institute of science and technology","correspondingAuthor":true,"prefix":"","firstName":"Tapasvi","middleName":"","lastName":"Panchagnula","suffix":""},{"id":609905032,"identity":"77bab013-3799-4d5b-871a-1b7de93a2c26","order_by":1,"name":"Shivani Reddy Alumalla","email":"","orcid":"","institution":"Sreenidhi Institute of science and technology","correspondingAuthor":false,"prefix":"","firstName":"Shivani","middleName":"Reddy","lastName":"Alumalla","suffix":""},{"id":609905033,"identity":"ca315004-8002-4d2d-8655-027bcbd4efb8","order_by":2,"name":"Indirala Surya","email":"","orcid":"","institution":"Sreenidhi Institute of science and technology","correspondingAuthor":false,"prefix":"","firstName":"Indirala","middleName":"","lastName":"Surya","suffix":""},{"id":609905034,"identity":"c5363565-3fc9-463c-82b2-591cb0e1c2a3","order_by":3,"name":"K. Divyasri","email":"","orcid":"","institution":"Sreenidhi Institute of science and technology","correspondingAuthor":false,"prefix":"","firstName":"K.","middleName":"","lastName":"Divyasri","suffix":""},{"id":609905035,"identity":"a6a18702-59ea-4e30-8ad1-8edb19e1e599","order_by":4,"name":"T. Venkat Narayana Rao","email":"","orcid":"https://orcid.org/0000-0002-1996-1819","institution":"Sreenidhi Institute of science and technology","correspondingAuthor":false,"prefix":"","firstName":"T.","middleName":"Venkat Narayana","lastName":"Rao","suffix":""}],"badges":[],"createdAt":"2026-03-21 14:41:09","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-9186511/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9186511/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105564592,"identity":"924688e8-89d9-464d-bef1-0ca3b3b5f701","added_by":"auto","created_at":"2026-03-27 12:50:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":364684,"visible":true,"origin":"","legend":"","description":"","filename":"LINPULSEZENODO.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9186511/v1_covered_8d3de1b9-f907-49c4-85e6-43d35d29d182.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eLinkPulse: A Hybrid Retrieval-Augmented Generation Platform for Autonomous Multi-Source Knowledge Synthesis\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Sreenidhi Institute of Science and Technology","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":"Retrieval-Augmented Generation, Hybrid Search, Multi-Agent Systems, Knowledge Synthesis, Large Language Models, Information Retrieval","lastPublishedDoi":"10.21203/rs.3.rs-9186511/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9186511/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eRetrieval-Augmented Generation (RAG) has emerged as a principled approach to grounding large language model (LLM) responses in external knowledge, yet deployed systems face three persistent limitations: (1) single-modality retrieval that degrades on semantically diverse queries; (2) fragmented knowledge sources that cannot unify static corpora with real-time web signals; and (3) monolithic architectures that resist component-level optimisation and scaling. We propose LinkPulse, an autonomous knowledge-synthesis platform that addresses these limitations through three technical contributions. First, the Tri-Modal Fusion Retriever (tmfr) dynamically weights dense vector similarity, sparse BM25 keyword matching, and live web-search signals via a lightweight learned gating network. Second, the Multi-Agent Ingestion Pipeline (maip) abstracts heterogeneous sources—web pages, GitHub repositories, PDFs, and multimedia—into a unified vector-indexed knowledge store with source-aware provenance tracking. Third, the Adaptive Context Window (acw) combines cross-encoder re-ranking with extractive sentence compression to reduce context dilution before generation. We evaluate LinkPulse on LinkPulse-Bench, a curated multi-domain benchmark of 150 queries spanning 1,000+ indexed documents across three content categories. On our benchmark, LinkPulse achieves an F1 score of 97.1, outperforming TF-IDF (+13.3 points), vector-only RAG (+3.4 points), and Self-RAG (+1.2 points), while reducing mean response latency to 230 ms and an observed hallucination rate of 3.2% on our test set. Ablation experiments confirm that each component contributes independently to performance. We release LinkPulse-Bench and all code to support reproducibility.\u003c/p\u003e","manuscriptTitle":"LinkPulse: A Hybrid Retrieval-Augmented Generation Platform for Autonomous Multi-Source Knowledge Synthesis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-24 06:35:48","doi":"10.21203/rs.3.rs-9186511/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":"222549dc-34a9-4937-b9e0-ea8cdfeefe6e","owner":[],"postedDate":"March 24th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":64902061,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-03-24T06:35:48+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-24 06:35:48","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9186511","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9186511","identity":"rs-9186511","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}