{"id":{"repo_id":"msu","oai_identifier":"oai:d.lib.msu.edu:etd_53325"},"canonical_url":"https://search.ndltd.org/etd/msu/oai:d.lib.msu.edu:etd_53325","repository":{"repo_id":"msu","name":"Michigan State University","base_url":"https://d.lib.msu.edu/oai"},"display":{"title":"DESIGNING AND EVALUATING A THEORY-DRIVEN AI LEARNING PARTNER FOR METACOGNITIVE REGULATION AND TRANSFER","abstract":"Thesis (Ph.D.)--Michigan State University. Educational Psychology and Educational Technology - Doctor of Philosophy, 2026","abstract_html":"Thesis (Ph.D.)--Michigan State University. Educational Psychology and Educational Technology - Doctor of Philosophy, 2026","abstract_has_math":false,"creators":["Lin, Qiyang"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Spiro, Rand","Cloude, Elizabeth","Ratan, Rabindra","Krajcik, Joseph"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-18T18:59:47Z","subjects":["Education"],"languages":["eng"],"rights":["In Copyright"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:53325","local:Lin_grad.msu_0128D_22379"],"render_values":[{"text":"etd:53325","href":null,"code":true},{"text":"local:Lin_grad.msu_0128D_22379","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/doi:10.25335/7g8y-vb74","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/doi:10.25335/7g8y-vb74","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://d.lib.msu.edu/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Ad.lib.msu.edu%3Aetd_53325","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Spiro, Rand","Cloude, Elizabeth","Ratan, Rabindra","Krajcik, Joseph"]},{"key":"dc:creator","label":"Author","values":["Lin, Qiyang"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:relation","label":"Dc Relation","values":["Electronic Theses & Dissertations"]},{"key":"dc:type","label":"Dc Type","values":["text","Electronic dissertations"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Education"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:53325","local:Lin_grad.msu_0128D_22379","https://doi.org/doi:10.25335/7g8y-vb74"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (Ph.D.)--Michigan State University. Educational Psychology and Educational Technology - Doctor of Philosophy, 2026","The rapid growth of Generative AI (GenAI) has created new opportunities to support learners’ metacognitive regulation and adaptive reasoning in complex, open-ended problems. Realizing this potential requires AI systems that do more than give answers. They must scaffold how learners plan, monitor, and evaluate their thinking under uncertainty. This dissertation designed, implemented, and evaluated a theory-driven AI learning partner intended to support undergraduates’ metacognitive regulation and transfer-oriented reasoning in pandemic decision-making. The design integrated Cognitive Flexibility Theory (CFT; Spiro et al., 2019) as the rationale for case variation, multiple perspectives, and context-sensitive prompting; Zimmerman’s (2000) self-regulated learning cycle as the temporal structure for organizing support; and Efklides’s (2008) and Tarricone’s (2011) models of metacognitive regulation as the process mechanism to be elicited and observed.The study used a mixed-methods, single-condition, multiple-case design. Five undergraduates completed four AI-supported learning sessions. Multimodal data sources were integrated to examine both the processes and outcomes of AI-supported learning, including concurrent think-aloud protocols, learner-AI chat logs, pre- and posttests, and transfer tasks. Findings are reported descriptively to support within-person and cross-case interpretation. Three research questions guided the analysis: how CFT and SRL principles were operationalized in the design and enacted behavior of the AI partner (RQ1), how learners externalized metacognitive regulation during interaction (RQ2), and how learners’ understanding and transfer-oriented reasoning developed across sessions (RQ3). Results show that the AI partner enacted theory-aligned scaffolding, but the dialogue emphasized SRL more strongly than CFT. Monitoring prompts were frequent, while cross-case linking was rare. Learners externalized sustained regulation but followed different trajectories. Transfer-oriented reasoning results show that one focal learner refined an already adaptive but broad frame toward more conditional decisions, while the other moved unevenly from reductive containment toward more context-sensitive coordination before reverting to avoidance under uncertainty. Together, the study contributes a theory-driven model for designing AI learning partners, an approach to operationalizing CFT through system prompts, and a multimodal method for observing regulation during human-AI interaction.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf","1 online resource (170 p.) : ill."]},{"key":"dc:title","label":"Title","values":["DESIGNING AND EVALUATING A THEORY-DRIVEN AI LEARNING PARTNER FOR METACOGNITIVE REGULATION AND TRANSFER"]}]}],"canonical_facts":{"dc:contributor":["Spiro, Rand","Cloude, Elizabeth","Ratan, Rabindra","Krajcik, Joseph"],"dc:creator":["Lin, Qiyang"],"dc:date":["2026"],"dc:description":["Thesis (Ph.D.)--Michigan State University. Educational Psychology and Educational Technology - Doctor of Philosophy, 2026","The rapid growth of Generative AI (GenAI) has created new opportunities to support learners’ metacognitive regulation and adaptive reasoning in complex, open-ended problems. Realizing this potential requires AI systems that do more than give answers. They must scaffold how learners plan, monitor, and evaluate their thinking under uncertainty. This dissertation designed, implemented, and evaluated a theory-driven AI learning partner intended to support undergraduates’ metacognitive regulation and transfer-oriented reasoning in pandemic decision-making. The design integrated Cognitive Flexibility Theory (CFT; Spiro et al., 2019) as the rationale for case variation, multiple perspectives, and context-sensitive prompting; Zimmerman’s (2000) self-regulated learning cycle as the temporal structure for organizing support; and Efklides’s (2008) and Tarricone’s (2011) models of metacognitive regulation as the process mechanism to be elicited and observed.The study used a mixed-methods, single-condition, multiple-case design. Five undergraduates completed four AI-supported learning sessions. Multimodal data sources were integrated to examine both the processes and outcomes of AI-supported learning, including concurrent think-aloud protocols, learner-AI chat logs, pre- and posttests, and transfer tasks. Findings are reported descriptively to support within-person and cross-case interpretation. Three research questions guided the analysis: how CFT and SRL principles were operationalized in the design and enacted behavior of the AI partner (RQ1), how learners externalized metacognitive regulation during interaction (RQ2), and how learners’ understanding and transfer-oriented reasoning developed across sessions (RQ3). Results show that the AI partner enacted theory-aligned scaffolding, but the dialogue emphasized SRL more strongly than CFT. Monitoring prompts were frequent, while cross-case linking was rare. Learners externalized sustained regulation but followed different trajectories. Transfer-oriented reasoning results show that one focal learner refined an already adaptive but broad frame toward more conditional decisions, while the other moved unevenly from reductive containment toward more context-sensitive coordination before reverting to avoidance under uncertainty. Together, the study contributes a theory-driven model for designing AI learning partners, an approach to operationalizing CFT through system prompts, and a multimodal method for observing regulation during human-AI interaction.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."],"dc:format":["application/pdf","1 online resource (170 p.) : ill."],"dc:identifier":["etd:53325","local:Lin_grad.msu_0128D_22379","https://doi.org/doi:10.25335/7g8y-vb74"],"dc:language":["eng"],"dc:relation":["Electronic Theses & Dissertations"],"dc:rights":["In Copyright"],"dc:subject":["Education"],"dc:title":["DESIGNING AND EVALUATING A THEORY-DRIVEN AI LEARNING PARTNER FOR METACOGNITIVE REGULATION AND TRANSFER"],"dc:type":["text","Electronic dissertations"]},"updated_at":"2026-11-18T18:59:47Z"}