NatBDI: Combining BDI Reasoning and Natural Language Inference for Autonomous Agents

NatBDI: Combining BDI Reasoning and Natural Language Inference for Autonomous Agents | 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 NatBDI: Combining BDI Reasoning and Natural Language Inference for Autonomous Agents Alexandre Yukio Ichida, Felipe Meneguzzi, Rafael C. Cardoso This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8990521/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Developing autonomous agents to deal with real-world problems is challenging, especially when developers are not necessarily specialists in artificial intelligence. Recent advances in machine learning to address natural language processing tasks are reaching performance levels suitable for practical applications, although these approaches rely on opaque and inscrutable models. This poses three key challenges: the interface of the programming with the developer, the efficiency of the resulting agents, and the scrutiny of their behaviour. Purpose: We tackle the challenge of developing autonomous agents over natural language environments in an efficient agent architecture that leverages recent developments in natural language processing, and the intuitive folk psychology abstraction of the beliefs, desires, intentions (BDI) architecture. Methods: This article introduces NatBDI, a new class of agent architecture that uses the BDI reasoning cycle with components driven by natural language processing. The resulting architecture handles natural language environments using a combination of language models and natural language inference to bootstrap the agent’s reasoning processing. Results: NatBDI agents leverage natural language components based on mental attitudes, enhancing intuitive understanding of the agent’s mental state. This allows a developer to instruct the agent more directly using a combination of controlled natural language structure and natural language knowledge as its programming interface.We empirically assess the efficiency gains of this combination while introducing a more intuitively programmed autonomous agent. Instructions in this interface substantially improve agent performance in the experimental scenario over a baseline agent created using a pure machine learning approach. Conclusion: The resulting architecture shows that combining learned policies with intuitively engineered domain knowledge yields substantial performance gains. We expect this class of agents to provide a powerful, yet intuitive, tool for agent-driven programming. belief-desire-intention natural language processing machine learning autonomous agents text-based environments Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 17 Apr, 2026 Reviewers agreed at journal 06 Apr, 2026 Reviewers agreed at journal 06 Apr, 2026 Reviewers invited by journal 06 Apr, 2026 Editor assigned by journal 03 Mar, 2026 Submission checks completed at journal 01 Mar, 2026 First submitted to journal 27 Feb, 2026 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-8990521","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":618229126,"identity":"3fd7a94b-b2cf-4d03-a73e-b119f6b6abfa","order_by":0,"name":"Alexandre Yukio Ichida","email":"","orcid":"","institution":"Pontifical Catholic University of Rio Grande do Sul","correspondingAuthor":false,"prefix":"","firstName":"Alexandre","middleName":"Yukio","lastName":"Ichida","suffix":""},{"id":618229127,"identity":"00120344-d5b4-4493-bef0-231c655bb89a","order_by":1,"name":"Felipe Meneguzzi","email":"data:image/png;base64,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","orcid":"","institution":"University of Aberdeen","correspondingAuthor":true,"prefix":"","firstName":"Felipe","middleName":"","lastName":"Meneguzzi","suffix":""},{"id":618229128,"identity":"ddaf0de2-3df6-4093-b306-51356e53885a","order_by":2,"name":"Rafael C. Cardoso","email":"","orcid":"","institution":"University of Aberdeen","correspondingAuthor":false,"prefix":"","firstName":"Rafael","middleName":"C.","lastName":"Cardoso","suffix":""}],"badges":[],"createdAt":"2026-02-27 17:23:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8990521/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8990521/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106725296,"identity":"1d850373-40f4-482d-ae27-d3d68af3928f","added_by":"auto","created_at":"2026-04-12 18:32:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":876433,"visible":true,"origin":"","legend":"","description":"","filename":"manuscriptJAAMAS.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8990521/v1_covered_7e499bcf-59ce-442b-9917-f1670dbffe0c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"NatBDI: Combining BDI Reasoning and Natural Language Inference for Autonomous Agents","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":"autonomous-agents-and-multi-agent-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"agnt","sideBox":"Learn more about [Autonomous Agents and Multi-Agent Systems](http://link.springer.com/journal/10458)","snPcode":"10458","submissionUrl":"https://submission.nature.com/new-submission/10458/3","title":"Autonomous Agents and Multi-Agent Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"belief-desire-intention, natural language processing, machine learning, autonomous agents, text-based environments","lastPublishedDoi":"10.21203/rs.3.rs-8990521/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8990521/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDeveloping autonomous agents to deal with real-world problems is challenging, especially when developers are not necessarily specialists in artificial intelligence. Recent advances in machine learning to address natural language processing tasks are reaching performance levels suitable for practical applications, although these approaches rely on opaque and inscrutable models. This poses three key challenges: the interface of the programming with the developer, the efficiency of the resulting agents, and the scrutiny of their behaviour.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003ePurpose: We tackle the challenge of developing autonomous agents over natural language environments in an efficient agent architecture that leverages recent developments in natural language processing, and the intuitive folk psychology abstraction of the beliefs, desires, intentions (BDI) architecture.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eMethods: This article introduces NatBDI, a new class of agent architecture that uses the BDI reasoning cycle with components driven by natural language processing. The resulting architecture handles natural language environments using a combination of language models and natural language inference to bootstrap the agent’s reasoning processing.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eResults: NatBDI agents leverage natural language components based on mental attitudes, enhancing intuitive understanding of the agent’s mental state. This allows a developer to instruct the agent more directly using a combination of controlled natural language structure and natural language knowledge as its programming interface.We empirically assess the efficiency gains of this combination while introducing a more intuitively programmed autonomous agent. Instructions in this interface substantially improve agent performance in the experimental scenario over a baseline agent created using a pure machine learning approach.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eConclusion: The resulting architecture shows that combining learned policies with intuitively engineered domain knowledge yields substantial performance gains. We expect this class of agents to provide a powerful, yet intuitive, tool for agent-driven programming.\u003c/p\u003e","manuscriptTitle":"NatBDI: Combining BDI Reasoning and Natural Language Inference for Autonomous Agents","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-10 03:51:35","doi":"10.21203/rs.3.rs-8990521/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"337628246025508955211958445248344676228","date":"2026-04-17T11:04:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"267399413106094297611572559677025376790","date":"2026-04-06T12:08:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"332459060500089130581804910628874379528","date":"2026-04-06T09:43:58+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-06T05:51:45+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-04T02:25:47+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-02T00:46:44+00:00","index":"","fulltext":""},{"type":"submitted","content":"Autonomous Agents and Multi-Agent Systems","date":"2026-02-27T17:07:04+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"autonomous-agents-and-multi-agent-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"agnt","sideBox":"Learn more about [Autonomous Agents and Multi-Agent Systems](http://link.springer.com/journal/10458)","snPcode":"10458","submissionUrl":"https://submission.nature.com/new-submission/10458/3","title":"Autonomous Agents and Multi-Agent Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"e018ab56-f179-44f9-8140-82dd665c4415","owner":[],"postedDate":"April 10th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-10T03:51:36+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-10 03:51:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8990521","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8990521","identity":"rs-8990521","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}