<\/p>\n\n\n\n
Large language models (LLMs) have made automated program repair (APR) increasingly practical for real-world bugs, but repairing directly from bug reports remains underconstrained. Bug reproduction tests (BRTs) help close this gap by turning a bug report into an executable, bug-specific signal that can guide repair and validate candidate patches. Existing work has therefore studied BRT generation as a core subproblem in APR and mainly evaluates a generated BRT using the fail-to-pass (F->P) criterion, which requires the test to fail on the buggy code but pass on the golden fix. We show that F->P alone is insufficient when the goal of a BRT is to improve downstream repair. In particular, some F->P BRTs are lax, reproducing the observed symptom yet still admitting plausible-but-incorrect patches. We formalize this missing quality dimension by separating F->P BRTs into rigorous and lax ones, and show empirically that only the former consistently improve repair success. We further find that co-generation introduces test–fix error coupling, where the in-trajectory fail-to-pass (F->P) check can pass even when both the generated patch and generated test are wrong. Based on these findings, we propose CoHarden, a co-generation framework that uses the Lax signal as an in-loop convergence criterion. CoHarden first generates a test before any fix, then iteratively hardens the test and fix against surviving mutation patches until the generated test no longer admits Lax regressions. Experiments show that CoHarden reaches 69.4% Resolved and 78.9% F->P on SWE-bench Verified, outperforming the strongest fix-only and cogeneration baselines by +9.6 and +7.9 percentage points in Resolved, respectively, with consistent gains across LLM backbones and benchmarks.<\/p>\n\n\n\n
<\/p>\n","protected":false},"excerpt":{"rendered":"
Large language models (LLMs) have made automated program repair (APR) increasingly practical for real-world bugs, but repairing directly from bug reports remains underconstrained. Bug reproduction tests (BRTs) help close this gap by turning a bug report into an executable, bug-specific signal that can guide repair and validate candidate patches. Existing work has therefore studied BRT […]<\/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":"text","value":"Yuhao Tan","user_id":0},{"type":"text","value":"Zhibang Yang","user_id":0},{"type":"user_nicename","value":"Fangkai Yang","user_id":"41425"},{"type":"text","value":"Yuan Yao","user_id":0},{"type":"user_nicename","value":"Yu Kang","user_id":"39381"},{"type":"user_nicename","value":"Lu Wang","user_id":"44027"},{"type":"user_nicename","value":"Pu Zhao","user_id":"38886"},{"type":"text","value":"Xin Zhang","user_id":0},{"type":"text","value":"Xiaoxing Ma","user_id":0},{"type":"text","value":"Qingwei Lin","user_id":0},{"type":"user_nicename","value":"Saravan Rajmohan","user_id":"41039"},{"type":"user_nicename","value":"Dongmei Zhang","user_id":"31665"}],"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"arXiv","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":"2607.19843","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":"2026-07-22","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":7,"msr_day":22,"msr_microsoftintellectualproperty":false,"msr_pub_id":"20feaa84e823cc8b63f531e4f2d5e8c9cfaff5c8","msr_publication_uploader":[{"type":"url","title":"https:\/\/arxiv.org\/abs\/2607.19843","label_id":243109,"id":false,"viewUrl":false}],"msr_related_uploader":[],"msr_original_fields_of_study":[],"msr_s2_paper_id":"20feaa84e823cc8b63f531e4f2d5e8c9cfaff5c8","msr_s2_pdf_url":"","msr_citation_count_updated":"","msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":36,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[{"provider":"s2","id":"20feaa84e823cc8b63f531e4f2d5e8c9cfaff5c8"},{"provider":"arxiv","id":"2607.19843"},{"provider":"corpusid","id":"290447008"}],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13556,13563],"msr-publication-type":[270373],"msr-publisher":[],"msr-publication-cta":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[256039,246691,265728],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1180646","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-data-platform-analytics","msr-locale-en_us","msr-field-of-study-artifcial-intelligence","msr-field-of-study-computer-science","msr-field-of-study-software-engineering-15"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2026-07-22","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":"arXiv","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":[{"type":"url","title":"https:\/\/arxiv.org\/abs\/2607.19843","label_id":243109,"id":false,"viewUrl":false}],"msr_related_uploader":[],"msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"20feaa84e823cc8b63f531e4f2d5e8c9cfaff5c8","msr_influential_citations":0,"msr_reference_count":36,"msr_arxiv_id":"2607.19843","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Yuhao Tan","user_id":0,"rest_url":false},{"type":"text","value":"Zhibang Yang","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Fangkai Yang","user_id":41425,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Fangkai Yang"},{"type":"text","value":"Yuan Yao","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Yu Kang","user_id":39381,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Yu Kang"},{"type":"user_nicename","value":"Lu Wang","user_id":44027,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Lu Wang"},{"type":"user_nicename","value":"Pu Zhao","user_id":38886,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Pu Zhao"},{"type":"text","value":"Xin Zhang","user_id":0,"rest_url":false},{"type":"text","value":"Xiaoxing Ma","user_id":0,"rest_url":false},{"type":"text","value":"Qingwei Lin","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Saravan Rajmohan","user_id":41039,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Saravan Rajmohan"},{"type":"user_nicename","value":"Dongmei Zhang","user_id":31665,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Dongmei Zhang"}],"msr_impact_theme":[],"msr_research_lab":[199560],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"misc","related_content":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1180646","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":3,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1180646\/revisions"}],"predecessor-version":[{"id":1180891,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1180646\/revisions\/1180891"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1180646"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=1180646"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1180646"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1180646"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=1180646"},{"taxonomy":"msr-publication-cta","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-cta?post=1180646"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1180646"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1180646"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1180646"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=1180646"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1180646"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1180646"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1180646"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1180646"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}