AI tutors are most useful when they adaptively respond to each student\u2019s strengths, weaknesses, and preferred kinds of guidance, but which guidance works for which student is a sparse signal, slow and costly to collect from real students. Student simulators can supply that signal as a proxy, yet existing ones cover only part of what this requires: state-tracking models fit how a student behaves but cannot digest a tutor\u2019s explanations or corrections well, while LLMs prompted to role-play a target student follow a tutor\u2019s guidance fluently but do not reliably reproduce the competence of the student they imitate. We present STUDENTSIM, a training framework that turns sparse per-student data into an individualized simulator for each student through a two-stage pipeline of pooled training followed by per-student specialization, so that the simulator both mirrors the student\u2019s own responses and updates them under tutor guidance. To measure these two abilities fairly, we build STUDENTSIMEVAL, a standardized protocol spanning 60 students across chess, second-language English writing, and mathematics, drawn from public learner datasets whose de-identified student records are shared for research. It scores every method on behavioral fidelity (F \u2191), how well a simulator matches a student\u2019s own responses, and guidance responsiveness (R \u2191), how readily it updates its response under a tutor\u2019s guidance, fitting each method on the same records and scoring it on the same held-out records so results are directly comparable; we release our construction and evaluation code so others can score new methods on the same benchmark and extend it. Across all three domains, our per-student simulators outperform GPT-5.4 on both metrics. In chess, for example, STUDENTSIM reaches F = 0.51 and R =0.91, compared with 0.23 and 0.72 for GPT-5.4 and 0.45 and 0.27 for Maia2, a skill-conditioned chess move prediction model. As a proof of concept that the framework also supports AI tutor improvement, a trained STUDENTSIM used as the reward for tutor model reinforcement learning yields a chess tutor that expert humans rate as more accurate, better-guided, and more personalized than both a no-RL baseline and a tutor RL-trained against a GPT-5.4 simulator reward.<\/p>\n","protected":false},"excerpt":{"rendered":"
AI tutors are most useful when they adaptively respond to each student\u2019s strengths, weaknesses, and preferred kinds of guidance, but which guidance works for which student is a sparse signal, slow and costly to collect from real students. Student simulators can supply that signal as a proxy, yet existing ones cover only part of what […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":[{"type":"guest","value":"ke-yang","user_id":"1163471"},{"type":"user_nicename","value":"Chenglong Wang","user_id":"41251"},{"type":"user_nicename","value":"Michel Galley","user_id":"32887"},{"type":"user_nicename","value":"Chandan Singh","user_id":"42126"},{"type":"user_nicename","value":"Jeevana Priya Inala","user_id":"41377"},{"type":"guest","value":"chengxiang-zhai","user_id":"1163472"},{"type":"user_nicename","value":"Jianfeng Gao","user_id":"32246"}],"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"","msr_doi":"","msr_arxiv_id":"","msr_mag_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_release_tracker_id":"","msr_highlight_type":"","msr_date_display_format":"","msr_main_download_label":"","msr_external_link_label":"","msr_doi_label":"","msr_published_date":"2026-09","msr_startdate":"","msr_presentation_date":"","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_year":2026,"msr_month":9,"msr_day":0,"msr_microsoftintellectualproperty":false,"msr_pub_id":"","msr_publication_uploader":[],"msr_related_uploader":[{"type":"file","title":"StudentSim.pdf","label_id":243112,"id":1186130,"viewUrl":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2026\/09\/StudentSim.pdf"},{"type":"url","title":"https:\/\/arxiv.org\/pdf\/2609.01591","label_id":243118,"id":false,"viewUrl":false},{"type":"url","title":"https:\/\/github.com\/microsoft\/StudentSim","label_id":264520,"id":false,"viewUrl":false}],"msr_original_fields_of_study":[],"msr_s2_paper_id":"","msr_s2_pdf_url":"","msr_citation_count_updated":"","msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13556],"msr-publication-type":[193726],"msr-publisher":[],"msr-publication-cta":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[270234],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1186128","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-field-of-study-artificial-intelligence-1024"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2026-09","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":0,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[],"msr_related_uploader":[{"type":"file","title":"StudentSim.pdf","label_id":243112,"id":1186130,"viewUrl":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2026\/09\/StudentSim.pdf"},{"type":"url","title":"https:\/\/arxiv.org\/pdf\/2609.01591","label_id":243118,"id":false,"viewUrl":false},{"type":"url","title":"https:\/\/github.com\/microsoft\/StudentSim","label_id":264520,"id":false,"viewUrl":false}],"msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[{"id":1186130,"url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2026\/09\/StudentSim.pdf"}],"msr-author-ordering":[{"type":"guest","value":"ke-yang","user_id":1163471,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=ke-yang"},{"type":"user_nicename","value":"Chenglong Wang","user_id":41251,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Chenglong Wang"},{"type":"user_nicename","value":"Michel Galley","user_id":32887,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Michel Galley"},{"type":"user_nicename","value":"Chandan Singh","user_id":42126,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Chandan Singh"},{"type":"user_nicename","value":"Jeevana Priya Inala","user_id":41377,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Jeevana Priya Inala"},{"type":"guest","value":"chengxiang-zhai","user_id":1163472,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=chengxiang-zhai"},{"type":"user_nicename","value":"Jianfeng Gao","user_id":32246,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Jianfeng Gao"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"unpublished","related_content":[],"_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1186128","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":3,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1186128\/revisions"}],"predecessor-version":[{"id":1186134,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1186128\/revisions\/1186134"}],"wp:attachment":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1186128"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=1186128"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1186128"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1186128"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=1186128"},{"taxonomy":"msr-publication-cta","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-cta?post=1186128"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1186128"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1186128"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1186128"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=1186128"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1186128"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1186128"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1186128"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1186128"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}