A Graph-Retrieval-Augmented Generation Framework Enhances Decision-Making in the Circular Economy

A Graph-Retrieval-Augmented Generation Framework Enhances Decision-Making in the Circular Economy | 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 Article A Graph-Retrieval-Augmented Generation Framework Enhances Decision-Making in the Circular Economy Yang Zhao, Chengxiao Dai, Dusit Niyato, Chuan Fu Tan, Keyi Xiang, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6795706/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 Large language models (LLMs) hold promise for sustainable manufacturing, but often hallucinate industrial codes and emission factors, undermining regulatory and investment decisions. We introduce CircuGraphRAG, a retrieval-augmented generation (RAG) framework that grounds LLMs outputs in a domain-specific knowledge graph for the circular economy. This graph connects 117,380 industrial and waste entities with classification codes and GWP100 emission data, enabling structured multi-hop reasoning. Natural language queries are translated into SPARQL and verified subgraphs are retrieved to ensure accuracy and traceability. Compared with Standalone LLMs and Naive RAG, CircuGraphRAG achieves superior performance in single-hop and multi-hop question answering, with ROUGE-L F1 scores up to 1.0, while baseline scores below 0.08. It also improves efficiency, halving the response time and reducing token usage by 16% in representative tasks. CircuGraphRAG provides fact-checked, regulatory-ready support for circular economy planning, advancing reliable, low-carbon resource decision making. Earth and environmental sciences/Environmental sciences/Environmental impact Physical sciences/Mathematics and computing/Computer science Circular Economy Large Language Model RAG GraphRAG Full Text Additional Declarations There is NO Competing Interest. 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-6795706","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":464781983,"identity":"c81a75fb-2676-4653-ab3d-202746002cd5","order_by":0,"name":"Yang Zhao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+0lEQVRIiWNgGAWjYDACCSBO4LGR44eLHCBGyweZNGPJBphqYrQwzrA5lGhwgFgt8rObHz7myTmQYHy8ge3xxzYGOb4bCcwfv+DRwjjnmLExz5k7eWZnDrAbHGxjMJa8kcAmLYNHC7NEgpk0b8+zYjOgSgmglsQNQAazBB4tbBLp36R5/x1O3Dz/AVhLPVAL82d8WngkcswkZ/AcTtwgwQDWkmBwI4FB8gMeLRISOcUGH3jSjCXOJLZJnDknYTjzzMM2aTw6GORnpG98AI7K9sPHJCrKbOT5jicf/vgDnx4EYGxggMQsYwMzD3FakHUTacsoGAWjYBSMDAAAUqhPnMcwyoQAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0003-0285-503X","institution":"Agency for Science, Technology and Research","correspondingAuthor":true,"prefix":"","firstName":"Yang","middleName":"","lastName":"Zhao","suffix":""},{"id":464781984,"identity":"af236cd0-b5be-4b1f-9653-b46c68ba6dba","order_by":1,"name":"Chengxiao Dai","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Chengxiao","middleName":"","lastName":"Dai","suffix":""},{"id":464781985,"identity":"afadc017-69c4-48fc-ae48-ef34db2b14b9","order_by":2,"name":"Dusit Niyato","email":"","orcid":"","institution":"Nanyang Technological University","correspondingAuthor":false,"prefix":"","firstName":"Dusit","middleName":"","lastName":"Niyato","suffix":""},{"id":464781986,"identity":"5e825fe2-bc80-407c-93e8-4f30cfd74bb6","order_by":3,"name":"Chuan Fu Tan","email":"","orcid":"","institution":"Agency for Science, Technology and Research (A*STAR)","correspondingAuthor":false,"prefix":"","firstName":"Chuan","middleName":"Fu","lastName":"Tan","suffix":""},{"id":464781987,"identity":"7d63a146-54c7-473f-b2f2-c234a28381fc","order_by":4,"name":"Keyi Xiang","email":"","orcid":"","institution":"Nanyang Technological University","correspondingAuthor":false,"prefix":"","firstName":"Keyi","middleName":"","lastName":"Xiang","suffix":""},{"id":464781988,"identity":"0c387ac8-6451-4e46-b590-a9b64551b39f","order_by":5,"name":"Yueyang Wang","email":"","orcid":"","institution":"National University of Singapore","correspondingAuthor":false,"prefix":"","firstName":"Yueyang","middleName":"","lastName":"Wang","suffix":""},{"id":464781989,"identity":"a49a04f4-ba7a-410e-9fc0-c1d3c12367bb","order_by":6,"name":"Zhiquan YEO","email":"","orcid":"","institution":"Singapore Institute of Manufacturing Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhiquan","middleName":"","lastName":"YEO","suffix":""},{"id":464781990,"identity":"da6237a3-961b-40cb-9d94-38ae8660b136","order_by":7,"name":"Daren TAN","email":"","orcid":"","institution":"Singapore Institute of Manufacturing Technology","correspondingAuthor":false,"prefix":"","firstName":"Daren","middleName":"","lastName":"TAN","suffix":""},{"id":464781991,"identity":"e20dd378-6294-4d22-a80f-b6eb5abd4762","order_by":8,"name":"Jonathan Low Zhaozhi","email":"","orcid":"","institution":"Agency for Science, Technology and Research (A*STAR)","correspondingAuthor":false,"prefix":"","firstName":"Jonathan","middleName":"Low","lastName":"Zhaozhi","suffix":""},{"id":464781992,"identity":"1607dc1b-e02a-4cff-89f2-bfd7cca7b437","order_by":9,"name":"Eugene HO","email":"","orcid":"","institution":"Singapore Institute of Manufacturing Technology","correspondingAuthor":false,"prefix":"","firstName":"Eugene","middleName":"","lastName":"HO","suffix":""}],"badges":[],"createdAt":"2025-06-01 12:50:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6795706/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6795706/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":83988834,"identity":"e2237415-5f05-43fb-828b-c7c7f6811899","added_by":"auto","created_at":"2025-06-05 11:53:33","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":880271,"visible":true,"origin":"","legend":"Article File","description":"","filename":"GraphRAGISnature.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6795706/v1_covered_3c6471bb-fbc8-43d8-a5c3-92e88c895051.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"A Graph-Retrieval-Augmented Generation Framework Enhances Decision-Making in the Circular Economy","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":"Circular Economy, Large Language Model, RAG, GraphRAG","lastPublishedDoi":"10.21203/rs.3.rs-6795706/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6795706/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Large language models (LLMs) hold promise for sustainable manufacturing, but often hallucinate industrial codes and emission factors, undermining regulatory and investment decisions. We introduce CircuGraphRAG, a retrieval-augmented generation (RAG) framework that grounds LLMs outputs in a domain-specific knowledge graph for the circular economy. This graph connects 117,380 industrial and waste entities with classification codes and GWP100 emission data, enabling structured multi-hop reasoning. Natural language queries are translated into SPARQL and verified subgraphs are retrieved to ensure accuracy and traceability. Compared with Standalone LLMs and Naive RAG, CircuGraphRAG achieves superior performance in single-hop and multi-hop question answering, with ROUGE-L F1 scores up to 1.0, while baseline scores below 0.08. It also improves efficiency, halving the response time and reducing token usage by 16% in representative tasks. CircuGraphRAG provides fact-checked, regulatory-ready support for circular economy planning, advancing reliable, low-carbon resource decision making.","manuscriptTitle":"A Graph-Retrieval-Augmented Generation Framework Enhances Decision-Making in the Circular Economy","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-03 02:32:18","doi":"10.21203/rs.3.rs-6795706/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":"6eabc7a5-d488-4a8e-b527-bca825d45083","owner":[],"postedDate":"June 3rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":49344892,"name":"Earth and environmental sciences/Environmental sciences/Environmental impact"},{"id":49344893,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2025-06-05T11:45:25+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-03 02:32:18","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6795706","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6795706","identity":"rs-6795706","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}