Feedback-Driven Automated Whole Bug Report Reproduction for Android Apps
In software development, bug report reproduction is a challenging task. This paper introduces ReBL, a novel feedback-driven approach that leverages GPT-4, a large-scale language model (LLM), to automatically reproduce Android bug reports. Unlike traditional methods, ReBL bypasses the use of Step to...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2024-08 |
|---|---|
| Hauptverfasser: | , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Wang, Dingbang Zhao, Yu Feng, Sidong Zhang, Zhaoxu Halfond, William G J Chen, Chunyang Sun, Xiaoxia Shi, Jiangfan Yu, Tingting |
| description | In software development, bug report reproduction is a challenging task. This paper introduces ReBL, a novel feedback-driven approach that leverages GPT-4, a large-scale language model (LLM), to automatically reproduce Android bug reports. Unlike traditional methods, ReBL bypasses the use of Step to Reproduce (S2R) entities. Instead, it leverages the entire textual bug report and employs innovative prompts to enhance GPT's contextual reasoning. This approach is more flexible and context-aware than the traditional step-by-step entity matching approach, resulting in improved accuracy and effectiveness. In addition to handling crash reports, ReBL has the capability of handling non-crash functional bug reports. Our evaluation of 96 Android bug reports (73 crash and 23 non-crash) demonstrates that ReBL successfully reproduced 90.63% of these reports, averaging only 74.98 seconds per bug report. Additionally, ReBL outperformed three existing tools in both success rate and speed. |
| doi_str_mv | 10.48550/arxiv.2407.05165 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2407_05165</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3077527090</sourcerecordid><originalsourceid>FETCH-LOGICAL-a520-2dae26867bef2de5eb0088ff6b19d5e4525ea203e0e9f9e5628b39f758d5da33</originalsourceid><addsrcrecordid>eNotj81Kw0AURgdBsNQ-gCsHXKfe3MnNJMtYrRUKggouw6RzR1PbTJwkRd_e_rj6NoePc4S4imGaZERwa8JPvZtiAnoKFKd0JkaoVBxlCeKFmHTdGgAw1UikRmIxZ7aVWX1F96HecSOLofdb07OV759-w_Ju-JAv3PrQHyZ4O6z62jfS-SCLxgZfW1m0bXcpzp3ZdDz537F4nT-8zRbR8vnxaVYsI0MIEVrDmGaprtihZeIKIMucS6s4t8QJIbFBUAycu5wpxaxSudOUWbJGqbG4Pr0eK8s21FsTfstDbXms3RM3J2Lv-j1w15drP4Rmr1Qq0JpQQw7qD5hkV1s</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3077527090</pqid></control><display><type>article</type><title>Feedback-Driven Automated Whole Bug Report Reproduction for Android Apps</title><source>Freely Accessible Journals</source><source>arXiv.org</source><creator>Wang, Dingbang ; Zhao, Yu ; Feng, Sidong ; Zhang, Zhaoxu ; Halfond, William G J ; Chen, Chunyang ; Sun, Xiaoxia ; Shi, Jiangfan ; Yu, Tingting</creator><creatorcontrib>Wang, Dingbang ; Zhao, Yu ; Feng, Sidong ; Zhang, Zhaoxu ; Halfond, William G J ; Chen, Chunyang ; Sun, Xiaoxia ; Shi, Jiangfan ; Yu, Tingting</creatorcontrib><description>In software development, bug report reproduction is a challenging task. This paper introduces ReBL, a novel feedback-driven approach that leverages GPT-4, a large-scale language model (LLM), to automatically reproduce Android bug reports. Unlike traditional methods, ReBL bypasses the use of Step to Reproduce (S2R) entities. Instead, it leverages the entire textual bug report and employs innovative prompts to enhance GPT's contextual reasoning. This approach is more flexible and context-aware than the traditional step-by-step entity matching approach, resulting in improved accuracy and effectiveness. In addition to handling crash reports, ReBL has the capability of handling non-crash functional bug reports. Our evaluation of 96 Android bug reports (73 crash and 23 non-crash) demonstrates that ReBL successfully reproduced 90.63% of these reports, averaging only 74.98 seconds per bug report. Additionally, ReBL outperformed three existing tools in both success rate and speed.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2407.05165</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computer Science - Software Engineering ; Debugging ; Feedback ; Large language models ; Software development</subject><ispartof>arXiv.org, 2024-08</ispartof><rights>2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,781,785,886,27930</link.rule.ids><backlink>$$Uhttps://doi.org/10.1145/3650212.3680341$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.2407.05165$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Wang, Dingbang</creatorcontrib><creatorcontrib>Zhao, Yu</creatorcontrib><creatorcontrib>Feng, Sidong</creatorcontrib><creatorcontrib>Zhang, Zhaoxu</creatorcontrib><creatorcontrib>Halfond, William G J</creatorcontrib><creatorcontrib>Chen, Chunyang</creatorcontrib><creatorcontrib>Sun, Xiaoxia</creatorcontrib><creatorcontrib>Shi, Jiangfan</creatorcontrib><creatorcontrib>Yu, Tingting</creatorcontrib><title>Feedback-Driven Automated Whole Bug Report Reproduction for Android Apps</title><title>arXiv.org</title><description>In software development, bug report reproduction is a challenging task. This paper introduces ReBL, a novel feedback-driven approach that leverages GPT-4, a large-scale language model (LLM), to automatically reproduce Android bug reports. Unlike traditional methods, ReBL bypasses the use of Step to Reproduce (S2R) entities. Instead, it leverages the entire textual bug report and employs innovative prompts to enhance GPT's contextual reasoning. This approach is more flexible and context-aware than the traditional step-by-step entity matching approach, resulting in improved accuracy and effectiveness. In addition to handling crash reports, ReBL has the capability of handling non-crash functional bug reports. Our evaluation of 96 Android bug reports (73 crash and 23 non-crash) demonstrates that ReBL successfully reproduced 90.63% of these reports, averaging only 74.98 seconds per bug report. Additionally, ReBL outperformed three existing tools in both success rate and speed.</description><subject>Computer Science - Software Engineering</subject><subject>Debugging</subject><subject>Feedback</subject><subject>Large language models</subject><subject>Software development</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotj81Kw0AURgdBsNQ-gCsHXKfe3MnNJMtYrRUKggouw6RzR1PbTJwkRd_e_rj6NoePc4S4imGaZERwa8JPvZtiAnoKFKd0JkaoVBxlCeKFmHTdGgAw1UikRmIxZ7aVWX1F96HecSOLofdb07OV759-w_Ju-JAv3PrQHyZ4O6z62jfS-SCLxgZfW1m0bXcpzp3ZdDz537F4nT-8zRbR8vnxaVYsI0MIEVrDmGaprtihZeIKIMucS6s4t8QJIbFBUAycu5wpxaxSudOUWbJGqbG4Pr0eK8s21FsTfstDbXms3RM3J2Lv-j1w15drP4Rmr1Qq0JpQQw7qD5hkV1s</recordid><startdate>20240828</startdate><enddate>20240828</enddate><creator>Wang, Dingbang</creator><creator>Zhao, Yu</creator><creator>Feng, Sidong</creator><creator>Zhang, Zhaoxu</creator><creator>Halfond, William G J</creator><creator>Chen, Chunyang</creator><creator>Sun, Xiaoxia</creator><creator>Shi, Jiangfan</creator><creator>Yu, Tingting</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240828</creationdate><title>Feedback-Driven Automated Whole Bug Report Reproduction for Android Apps</title><author>Wang, Dingbang ; Zhao, Yu ; Feng, Sidong ; Zhang, Zhaoxu ; Halfond, William G J ; Chen, Chunyang ; Sun, Xiaoxia ; Shi, Jiangfan ; Yu, Tingting</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a520-2dae26867bef2de5eb0088ff6b19d5e4525ea203e0e9f9e5628b39f758d5da33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Software Engineering</topic><topic>Debugging</topic><topic>Feedback</topic><topic>Large language models</topic><topic>Software development</topic><toplevel>online_resources</toplevel><creatorcontrib>Wang, Dingbang</creatorcontrib><creatorcontrib>Zhao, Yu</creatorcontrib><creatorcontrib>Feng, Sidong</creatorcontrib><creatorcontrib>Zhang, Zhaoxu</creatorcontrib><creatorcontrib>Halfond, William G J</creatorcontrib><creatorcontrib>Chen, Chunyang</creatorcontrib><creatorcontrib>Sun, Xiaoxia</creatorcontrib><creatorcontrib>Shi, Jiangfan</creatorcontrib><creatorcontrib>Yu, Tingting</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wang, Dingbang</au><au>Zhao, Yu</au><au>Feng, Sidong</au><au>Zhang, Zhaoxu</au><au>Halfond, William G J</au><au>Chen, Chunyang</au><au>Sun, Xiaoxia</au><au>Shi, Jiangfan</au><au>Yu, Tingting</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Feedback-Driven Automated Whole Bug Report Reproduction for Android Apps</atitle><jtitle>arXiv.org</jtitle><date>2024-08-28</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>In software development, bug report reproduction is a challenging task. This paper introduces ReBL, a novel feedback-driven approach that leverages GPT-4, a large-scale language model (LLM), to automatically reproduce Android bug reports. Unlike traditional methods, ReBL bypasses the use of Step to Reproduce (S2R) entities. Instead, it leverages the entire textual bug report and employs innovative prompts to enhance GPT's contextual reasoning. This approach is more flexible and context-aware than the traditional step-by-step entity matching approach, resulting in improved accuracy and effectiveness. In addition to handling crash reports, ReBL has the capability of handling non-crash functional bug reports. Our evaluation of 96 Android bug reports (73 crash and 23 non-crash) demonstrates that ReBL successfully reproduced 90.63% of these reports, averaging only 74.98 seconds per bug report. Additionally, ReBL outperformed three existing tools in both success rate and speed.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2407.05165</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2024-08 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_arxiv_primary_2407_05165 |
| source | Freely Accessible Journals; arXiv.org |
| subjects | Computer Science - Software Engineering Debugging Feedback Large language models Software development |
| title | Feedback-Driven Automated Whole Bug Report Reproduction for Android Apps |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-13T13%3A08%3A54IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Feedback-Driven%20Automated%20Whole%20Bug%20Report%20Reproduction%20for%20Android%20Apps&rft.jtitle=arXiv.org&rft.au=Wang,%20Dingbang&rft.date=2024-08-28&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2407.05165&rft_dat=%3Cproquest_arxiv%3E3077527090%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3077527090&rft_id=info:pmid/&rfr_iscdi=true |