{"id":925401,"date":"2023-03-07T12:06:17","date_gmt":"2023-03-07T20:06:17","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/"},"modified":"2023-05-08T16:54:32","modified_gmt":"2023-05-08T23:54:32","slug":"codamosa-escaping-coverage-plateaus-in-test-generation-with-pre-trained-large-language-models","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/codamosa-escaping-coverage-plateaus-in-test-generation-with-pre-trained-large-language-models\/","title":{"rendered":"CODAMOSA: Escaping Coverage Plateaus in Test Generation with Pre-trained Large Language Models"},"content":{"rendered":"

Search-based software testing (SBST) generates high-coverage test cases for programs under test with a combination of test case generation and mutation. SBST\u2019s performance relies on there being a reasonable probability of generating test cases that exercise the core logic of the program under test. Given such test cases, SBST can then explore the space around them to exercise various parts of the program. This paper explores whether Large Language Models (LLMs) of code, such as OpenAI\u2019s Codex, can be used to help SBST\u2019s exploration. Our proposed algorithm, CODAMOSA, conducts SBST until its coverage improvements stall, then asks Codex to provide example test cases for under-covered functions. These examples help SBST redirect its search to more useful areas of the search space. On an evaluation over 486 benchmarks, CODAMOSA achieves statistically significantly higher coverage on many more benchmarks (173 and 279) than it reduces coverage on (10 and 4), compared to SBST and LLM-only baselines.<\/p>\n","protected":false},"excerpt":{"rendered":"

Search-based software testing (SBST) generates high-coverage test cases for programs under test with a combination of test case generation and mutation. SBST\u2019s performance relies on there being a reasonable probability of generating test cases that exercise the core logic of the program under test. Given such test cases, SBST can then explore the space around […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13560],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[],"msr-conference":[259390],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-925401","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-programming-languages-software-engineering","msr-locale-en_us"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2023-5-17","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":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/03\/codamosa_icse23.pdf","id":"925404","title":"codamosa_icse23","label_id":"252679","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":925404,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/03\/codamosa_icse23.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"Caroline Lemieux","user_id":40777,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Caroline Lemieux"},{"type":"user_nicename","value":"Jeevana Priya Inala","user_id":41377,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Jeevana Priya Inala"},{"type":"user_nicename","value":"Shuvendu Lahiri","user_id":33640,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Shuvendu Lahiri"},{"type":"user_nicename","value":"Siddhartha Sen","user_id":33656,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Siddhartha Sen"}],"msr_impact_theme":[],"msr_research_lab":[199565,199571],"msr_event":[],"msr_group":[144812],"msr_project":[890049],"publication":[],"video":[],"download":[925395],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/925401"}],"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":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/925401\/revisions"}],"predecessor-version":[{"id":925407,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/925401\/revisions\/925407"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=925401"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=925401"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=925401"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=925401"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=925401"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=925401"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=925401"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=925401"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=925401"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=925401"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=925401"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=925401"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=925401"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=925401"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=925401"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}