Homo Silicus is Hyper-Rational: Why LLM Agents Fail to Replicate Attention-Driven Trading

Homo Silicus is Hyper-Rational: Why LLM Agents Fail to Replicate Attention-Driven Trading | 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 Homo Silicus is Hyper-Rational: Why LLM Agents Fail to Replicate Attention-Driven Trading John Garcia This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9372266/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 Can large language model (LLM) agents serve as proxies for human investors in behavioral finance experiments? I deploy 96 GPT-4-family agents in a staggered difference-in-differences design, exposing treated agents to exogenous attention shocks and viral social media signals about meme stocks while holding the fundamentals constant. Whereas human retail investors substantially increase net purchases of attention-grabbing stocks, LLM agents reduce buying propensity by 11.67 percentage points (SE = 4.92, p = .018), equivalent to preventing one purchase for every 8.6 treated agent-period observations. The direction and magnitude of this effect are robust across all specifications, although conservative small-sample variance corrections widen the confidence interval. Agents also display a reversed disposition effect, selling losers 3:1 relative to winners, directly contradicting the human pattern driven by loss aversion. To explain these divergences, I develop the Normative-Descriptive Divergence (NDD) model, formalizing how prescriptive training corpora ('avoid hype,' 'cut losses') generate systematic departures from the emotion-driven behavior observed in human investors. Even when explicitly prompted to exhibit FOMO, agents rationally retreat when attention shocks impose calculable costs, revealing a strict constraint hierarchy in which quantitative optimization overrides persona-level instructions. These findings establish boundary conditions for “Homo Silicus” research: LLMs approximate normative economic benchmarks but fail to replicate biases rooted in emotional processing. Investor attention retail trading behavioral finance Generative AI difference-in-differences LLM agents Full Text Additional Declarations No competing interests reported. Supplementary Files OnlineAppendix1GLEESImplementation.pdf 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-9372266","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":624935368,"identity":"22bf08e9-bad6-4dfb-99cb-640b5b43f77e","order_by":0,"name":"John Garcia","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+UlEQVRIiWNgGAWjYBACxgYQacAgx8DA3HiAgeEAVJyNsBZjEPMAQwIRWmAgsYFoLcz9i599+FFgl97ffrDhMO+PO3Lm7WcPMHwoO4zbYTOeGc/sMUjOnXEmseEwT8IzY5kzeQmMM87h03LAmJnBgDl3AwNYy+HEGQw5Bsy8bfi0HP8M1FKfbsD/EKylfgb/GwPmv/i09PeAbDmcYCABsSVBQgJoCyNeW3iKGXsMjhvOuPGw4eCctMOGMyTeGBzsOZeOU4th//HNDD/+VMvz9ycffPDG5rC8BH+O4YMfZda4tcxIwCJ6AKd6IJDnxys9CkbBKBgFowAIAMMJXPNtw8nxAAAAAElFTkSuQmCC","orcid":"","institution":"California Lutheran University","correspondingAuthor":true,"prefix":"","firstName":"John","middleName":"","lastName":"Garcia","suffix":""}],"badges":[],"createdAt":"2026-04-09 20:23:59","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9372266/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9372266/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107705784,"identity":"90cfd9ce-1d27-45ca-8d7a-905f46e02249","added_by":"auto","created_at":"2026-04-24 09:15:16","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1102141,"visible":true,"origin":"","legend":"","description":"","filename":"HomoSilicusisHyperRationalManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9372266/v1_covered_f0cbd7e2-db2b-4378-a5a7-c5c947371284.pdf"},{"id":107600178,"identity":"8e954161-bce3-49de-8f88-e0cabaf5eaff","added_by":"auto","created_at":"2026-04-23 06:27:16","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":4104110,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineAppendix1GLEESImplementation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9372266/v1/7056605ccd504dc94c88f7d6.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Homo Silicus is Hyper-Rational: Why LLM Agents Fail to Replicate Attention-Driven Trading","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Investor attention, retail trading, behavioral finance, Generative AI, difference-in-differences, LLM agents","lastPublishedDoi":"10.21203/rs.3.rs-9372266/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9372266/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eCan large language model (LLM) agents serve as proxies for human investors in behavioral finance experiments? I deploy 96 GPT-4-family agents in a staggered difference-in-differences design, exposing treated agents to exogenous attention shocks and viral social media signals about meme stocks while holding the fundamentals constant. Whereas human retail investors substantially increase net purchases of attention-grabbing stocks, LLM agents reduce buying propensity by 11.67 percentage points (SE\u0026thinsp;=\u0026thinsp;4.92, \u003cem\u003ep\u003c/em\u003e = .018), equivalent to preventing one purchase for every 8.6 treated agent-period observations. The direction and magnitude of this effect are robust across all specifications, although conservative small-sample variance corrections widen the confidence interval. Agents also display a reversed disposition effect, selling losers 3:1 relative to winners, directly contradicting the human pattern driven by loss aversion. To explain these divergences, I develop the Normative-Descriptive Divergence (NDD) model, formalizing how prescriptive training corpora ('avoid hype,' 'cut losses') generate systematic departures from the emotion-driven behavior observed in human investors. Even when explicitly prompted to exhibit FOMO, agents rationally retreat when attention shocks impose calculable costs, revealing a strict constraint hierarchy in which quantitative optimization overrides persona-level instructions. These findings establish boundary conditions for \u0026ldquo;Homo Silicus\u0026rdquo; research: LLMs approximate normative economic benchmarks but fail to replicate biases rooted in emotional processing.\u003c/p\u003e","manuscriptTitle":"Homo Silicus is Hyper-Rational: Why LLM Agents Fail to Replicate Attention-Driven Trading","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-23 06:27:12","doi":"10.21203/rs.3.rs-9372266/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":"6a10ec9e-0926-4543-b722-15fd18d1c259","owner":[],"postedDate":"April 23rd, 2026","published":true,"recentEditorialEvents":[{"type":"reviewerAgreed","content":"262346618484179239275784071334663864208","date":"2026-05-08T15:54:19+00:00","index":27,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-23T06:27:13+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-23 06:27:12","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9372266","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9372266","identity":"rs-9372266","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}