{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/140614"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/140614","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Towards Human-AI Teaming for Skill Development: From Dyadic Interview Practice to Triadic Programming Collaboration","abstract":"As the job market for CS graduates grows increasingly competitive, effective preparation for technical interviews through mock interviews and programming practice has become critical. This thesis explores how AI can support skill development in these domains, progressing from AI as a sole practice partner to AI as a collaborative teammate. Our first two studies investigate LLM-based conversational AI for interview preparation. Study 1 developed an interview system grounded in reflective learning and dialogic feedback, enabling learners to engage in low-stakes practice with personalized, interactive feedback. Study 2 extended this work to technical interviews, exploring how conversational AI can support the think-aloud practice in technical interviews through simulation, feedback, and example. Together, these studies demonstrate the value of AI as a dyadic practice partner. However, participants reported that while AI practice was useful, peer-based engagement may offer stronger social connection and motivation, suggesting that AI should augment rather than replace human collaboration. This insight motivated our third study, which investigates human–AI teaming in a triadic configuration. We introduce human–human–AI triadic programming, where two humans collaborate with a proactive AI agent. Results from 20 participants show that this triadic collaboration improves collaborative learning and social presence while encouraging more responsible AI use. Together, these studies advance understanding of how AI can support skill development, illustrating a trajectory from dyadic human–AI interaction toward richer forms of human–AI teaming that preserve the pedagogical and social benefits of human collaboration.","abstract_html":"As the job market for CS graduates grows increasingly competitive, effective preparation for technical interviews through mock interviews and programming practice has become critical. This thesis explores how AI can support skill development in these domains, progressing from AI as a sole practice partner to AI as a collaborative teammate. Our first two studies investigate LLM-based conversational AI for interview preparation. Study 1 developed an interview system grounded in reflective learning and dialogic feedback, enabling learners to engage in low-stakes practice with personalized, interactive feedback. Study 2 extended this work to technical interviews, exploring how conversational AI can support the think-aloud practice in technical interviews through simulation, feedback, and example. Together, these studies demonstrate the value of AI as a dyadic practice partner. However, participants reported that while AI practice was useful, peer-based engagement may offer stronger social connection and motivation, suggesting that AI should augment rather than replace human collaboration. This insight motivated our third study, which investigates human–AI teaming in a triadic configuration. We introduce human–human–AI triadic programming, where two humans collaborate with a proactive AI agent. Results from 20 participants show that this triadic collaboration improves collaborative learning and social presence while encouraging more responsible AI use. Together, these studies advance understanding of how AI can support skill development, illustrating a trajectory from dyadic human–AI interaction toward richer forms of human–AI teaming that preserve the pedagogical and social benefits of human collaboration.","abstract_has_math":false,"creators":["Daryanto, Taufiq Husada"],"institution":"Virginia Tech","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Computer Science & Applications","degree_department":"Computer Science and#38; Applications","school":null,"contributors":[],"advisors":[],"committee_chairs":["Rho, Ha Rim"],"committee_members":["Brown, Dwayne Christian","Chen, Yan"],"year":2026,"date_issued":"2026-01-06","date_published":"2026-01-06","updated_at":"2026-07-22T22:20:27Z","subjects":["human-AI interaction","interview practice","collaborative programming"],"languages":["en"],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:45422"],"render_values":[{"text":"vt_gsexam:45422","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10919/140614","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Rho, Ha Rim"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Brown, Dwayne Christian","Chen, Yan"]},{"key":"dc:contributor.department","label":"Department","values":["Computer Science and#38; Applications"]},{"key":"dc:creator","label":"Author","values":["Daryanto, Taufiq Husada"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-01-07T09:01:01Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-01-07T09:01:01Z"]},{"key":"dc:date.issued","label":"Date","values":["2026-01-06"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science & Applications"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["human-AI interaction","interview practice","collaborative programming"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:45422"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10919/140614"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["As the job market for CS graduates grows increasingly competitive, effective preparation for technical interviews through mock interviews and programming practice has become critical. This thesis explores how AI can support skill development in these domains, progressing from AI as a sole practice partner to AI as a collaborative teammate. Our first two studies investigate LLM-based conversational AI for interview preparation. Study 1 developed an interview system grounded in reflective learning and dialogic feedback, enabling learners to engage in low-stakes practice with personalized, interactive feedback. Study 2 extended this work to technical interviews, exploring how conversational AI can support the think-aloud practice in technical interviews through simulation, feedback, and example. Together, these studies demonstrate the value of AI as a dyadic practice partner. However, participants reported that while AI practice was useful, peer-based engagement may offer stronger social connection and motivation, suggesting that AI should augment rather than replace human collaboration. This insight motivated our third study, which investigates human–AI teaming in a triadic configuration. We introduce human–human–AI triadic programming, where two humans collaborate with a proactive AI agent. Results from 20 participants show that this triadic collaboration improves collaborative learning and social presence while encouraging more responsible AI use. Together, these studies advance understanding of how AI can support skill development, illustrating a trajectory from dyadic human–AI interaction toward richer forms of human–AI teaming that preserve the pedagogical and social benefits of human collaboration."]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["As the job market for computer science (CS) graduates becomes increasingly competitive, developing technical and communication skills is essential. Artificial intelligence (AI), particularly large language models (LLMs), offers a promising way to support this process. Yet little is known about how users perceive LLM-based interview practice support or what design considerations should guide their development. Therefore, our first study developed an LLM-based interview practice system grounded in reflective learning and dialogic feedback, followed by exploratory user studies. Our second study extended this work by exploring how conversational AI can support technical interview preparation through technical interview simulation, feedback, and examples. Together, these studies demonstrate the potential of conversational AI as a partner for interview preparation, enabling low-stakes practice with personalized feedback. However, our users also expressed a preference for practicing with peers, which potentially provides a better learning experience. Hence, this raises a question: rather than replacing human partners, can AI augment a peer-based practice while preserving the social and pedagogical benefits of collaboration? This question motivated our exploration of human–AI teaming, where AI is treated as a teammate and interactions can extend beyond dyadic settings. Building on this insight, our third study investigated human–human–AI triadic programming, where two humans collaborate with a proactive AI agent. Results from 20 participants show that this triadic collaboration improves collaborative learning and social presence, while encouraging more responsible AI use."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:title","label":"Title","values":["Towards Human-AI Teaming for Skill Development: From Dyadic Interview Practice to Triadic Programming Collaboration"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Rho, Ha Rim"],"dc:contributor.committeemember":["Brown, Dwayne Christian","Chen, Yan"],"dc:contributor.department":["Computer Science and#38; Applications"],"dc:creator":["Daryanto, Taufiq Husada"],"dc:date.accessioned":["2026-01-07T09:01:01Z"],"dc:date.available":["2026-01-07T09:01:01Z"],"dc:date.issued":["2026-01-06"],"dc:description.abstract":["As the job market for CS graduates grows increasingly competitive, effective preparation for technical interviews through mock interviews and programming practice has become critical. This thesis explores how AI can support skill development in these domains, progressing from AI as a sole practice partner to AI as a collaborative teammate. Our first two studies investigate LLM-based conversational AI for interview preparation. Study 1 developed an interview system grounded in reflective learning and dialogic feedback, enabling learners to engage in low-stakes practice with personalized, interactive feedback. Study 2 extended this work to technical interviews, exploring how conversational AI can support the think-aloud practice in technical interviews through simulation, feedback, and example. Together, these studies demonstrate the value of AI as a dyadic practice partner. However, participants reported that while AI practice was useful, peer-based engagement may offer stronger social connection and motivation, suggesting that AI should augment rather than replace human collaboration. This insight motivated our third study, which investigates human–AI teaming in a triadic configuration. We introduce human–human–AI triadic programming, where two humans collaborate with a proactive AI agent. Results from 20 participants show that this triadic collaboration improves collaborative learning and social presence while encouraging more responsible AI use. Together, these studies advance understanding of how AI can support skill development, illustrating a trajectory from dyadic human–AI interaction toward richer forms of human–AI teaming that preserve the pedagogical and social benefits of human collaboration."],"dc:description.abstractgeneral":["As the job market for computer science (CS) graduates becomes increasingly competitive, developing technical and communication skills is essential. Artificial intelligence (AI), particularly large language models (LLMs), offers a promising way to support this process. Yet little is known about how users perceive LLM-based interview practice support or what design considerations should guide their development. Therefore, our first study developed an LLM-based interview practice system grounded in reflective learning and dialogic feedback, followed by exploratory user studies. Our second study extended this work by exploring how conversational AI can support technical interview preparation through technical interview simulation, feedback, and examples. Together, these studies demonstrate the potential of conversational AI as a partner for interview preparation, enabling low-stakes practice with personalized feedback. However, our users also expressed a preference for practicing with peers, which potentially provides a better learning experience. Hence, this raises a question: rather than replacing human partners, can AI augment a peer-based practice while preserving the social and pedagogical benefits of collaboration? This question motivated our exploration of human–AI teaming, where AI is treated as a teammate and interactions can extend beyond dyadic settings. Building on this insight, our third study investigated human–human–AI triadic programming, where two humans collaborate with a proactive AI agent. Results from 20 participants show that this triadic collaboration improves collaborative learning and social presence, while encouraging more responsible AI use."],"dc:description.degree":["Master of Science"],"dc:format.medium":["ETD"],"dc:identifier.other":["vt_gsexam:45422"],"dc:identifier.uri":["https://hdl.handle.net/10919/140614"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["human-AI interaction","interview practice","collaborative programming"],"dc:title":["Towards Human-AI Teaming for Skill Development: From Dyadic Interview Practice to Triadic Programming Collaboration"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science & Applications"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:20:27Z"}