{"id":{"repo_id":"vilnius","oai_identifier":"oai:vu.lt:elaba:308337681"},"canonical_url":"https://search.ndltd.org/etd/vilnius/oai:vu.lt:elaba:308337681","repository":{"repo_id":"vilnius","name":"Vilnius University","base_url":"https://epublications.vu.lt/oai"},"display":{"title":"Iteracinis testų generavimo patikimumo užtikrinimo metodas /","abstract":"This thesis examines the reliability problem of unit test generation. Automatically generated tests can execute successfully and achieve high code coverage, but still fail to detect changes in program behavior. For this reason, the thesis proposes an iterative method for test generation reliability assurance based on mutation testing feedback. The main idea of the method is to use surviving mutants as concrete test generation targets. For each mutant, priority features are calculated: mutation operator, cyclomatic complexity of the function, function fan­-in, and the number of tests covering the mutant. Based on these features, a prioritized set of mutants is created, and a large language model receives the target mutant information and generates a test artifact change. The method was implemented as a prototype and evaluated in two experiments. In the first experiment, the method was applied to an initial test suite written by programmers, and the mutation score increased from 63.69% to 90.48%. In the second experiment, the test suite was created from an empty state and reached a mutation score of 93.71%. The experiments showed that mutation testing feedback can be used for large language model based test generation. However, accepting the final change requires checking not only whether the test suite executes successfully and the target mutant is killed, but also the overall mutation testing result of the test suite to prevent regressions in the test suite.","abstract_html":"This thesis examines the reliability problem of unit test generation. Automatically generated tests can execute successfully and achieve high code coverage, but still fail to detect changes in program behavior. For this reason, the thesis proposes an iterative method for test generation reliability assurance based on mutation testing feedback. The main idea of the method is to use surviving mutants as concrete test generation targets. For each mutant, priority features are calculated: mutation operator, cyclomatic complexity of the function, function fan­-in, and the number of tests covering the mutant. Based on these features, a prioritized set of mutants is created, and a large language model receives the target mutant information and generates a test artifact change. The method was implemented as a prototype and evaluated in two experiments. In the first experiment, the method was applied to an initial test suite written by programmers, and the mutation score increased from 63.69% to 90.48%. In the second experiment, the test suite was created from an empty state and reached a mutation score of 93.71%. The experiments showed that mutation testing feedback can be used for large language model based test generation. However, accepting the final change requires checking not only whether the test suite executes successfully and the target mutant is killed, but also the overall mutation testing result of the test suite to prevent regressions in the test suite.","abstract_has_math":false,"creators":["Kurlinskas, Astijus,"],"institution":"Institutional Repository of Vilnius University","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-19T10:12:59Z","subjects":[],"languages":["lit"],"rights":["info:eu-repo/semantics/openAccess"],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://repository.vu.lt/VU:ELABAETD308337681&prefLang=en_US","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://repository.vu.lt/VU:ELABAETD308337681&prefLang=en_US","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":"open","embargo_until":null,"access_note":null},"source_record":{"url":"https://epublications.vu.lt/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Avu.lt%3Aelaba%3A308337681","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Kurlinskas, Astijus,"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:publisher","label":"Institution","values":["Institutional Repository of Vilnius University"]},{"key":"dc:relation","label":"Dc Relation","values":["https://epublications.vu.lt/object/elaba:308337681/308337681.pdf"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/bachelorThesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["lit"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/openAccess"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://repository.vu.lt/VU:ELABAETD308337681&prefLang=en_US"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This thesis examines the reliability problem of unit test generation. Automatically generated tests can execute successfully and achieve high code coverage, but still fail to detect changes in program behavior. For this reason, the thesis proposes an iterative method for test generation reliability assurance based on mutation testing feedback. The main idea of the method is to use surviving mutants as concrete test generation targets. For each mutant, priority features are calculated: mutation operator, cyclomatic complexity of the function, function fan­-in, and the number of tests covering the mutant. Based on these features, a prioritized set of mutants is created, and a large language model receives the target mutant information and generates a test artifact change. The method was implemented as a prototype and evaluated in two experiments. In the first experiment, the method was applied to an initial test suite written by programmers, and the mutation score increased from 63.69% to 90.48%. In the second experiment, the test suite was created from an empty state and reached a mutation score of 93.71%. The experiments showed that mutation testing feedback can be used for large language model based test generation. However, accepting the final change requires checking not only whether the test suite executes successfully and the target mutant is killed, but also the overall mutation testing result of the test suite to prevent regressions in the test suite."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Iteracinis testų generavimo patikimumo užtikrinimo metodas /","Iterative method for test generation reliability assurance."]}]}],"canonical_facts":{"dc:creator":["Kurlinskas, Astijus,"],"dc:date":["2026"],"dc:description":["This thesis examines the reliability problem of unit test generation. Automatically generated tests can execute successfully and achieve high code coverage, but still fail to detect changes in program behavior. For this reason, the thesis proposes an iterative method for test generation reliability assurance based on mutation testing feedback. The main idea of the method is to use surviving mutants as concrete test generation targets. For each mutant, priority features are calculated: mutation operator, cyclomatic complexity of the function, function fan­-in, and the number of tests covering the mutant. Based on these features, a prioritized set of mutants is created, and a large language model receives the target mutant information and generates a test artifact change. The method was implemented as a prototype and evaluated in two experiments. In the first experiment, the method was applied to an initial test suite written by programmers, and the mutation score increased from 63.69% to 90.48%. In the second experiment, the test suite was created from an empty state and reached a mutation score of 93.71%. The experiments showed that mutation testing feedback can be used for large language model based test generation. However, accepting the final change requires checking not only whether the test suite executes successfully and the target mutant is killed, but also the overall mutation testing result of the test suite to prevent regressions in the test suite."],"dc:format":["application/pdf"],"dc:identifier":["https://repository.vu.lt/VU:ELABAETD308337681&prefLang=en_US"],"dc:language":["lit"],"dc:publisher":["Institutional Repository of Vilnius University"],"dc:relation":["https://epublications.vu.lt/object/elaba:308337681/308337681.pdf"],"dc:rights":["info:eu-repo/semantics/openAccess"],"dc:title":["Iteracinis testų generavimo patikimumo užtikrinimo metodas /","Iterative method for test generation reliability assurance."],"dc:type":["info:eu-repo/semantics/bachelorThesis"]},"updated_at":"2026-11-19T10:12:59Z"}