Academic Journal
LLMs and fuzzing in tandem: a new approach to automatically generating weakest preconditions.
| Title: | LLMs and fuzzing in tandem: a new approach to automatically generating weakest preconditions. |
|---|---|
| Authors: | King, Daragh, Koutavas, Vasileios, Kovács, Laura |
| Source: | International Journal on Software Tools for Technology Transfer; Jun2026, Vol. 28 Issue 3, p317-328, 12p |
| Subject Terms: | Software verification, Computer software testing, Java programming language, Language models, Computer software |
| Abstract: | The weakest precondition (WP) of a program describes the largest set of initial states from which all terminating executions of the program satisfy a given postcondition. The generation of WPs is an important task with practical applications in areas ranging from verification to run-time error checking. This paper proposes the combination of Large Language Models (LLMs) and fuzz testing for generating WPs. In pursuit of this goal, we introduce Fuzzing Guidance (FG); FG acts as a means of directing LLMs towards correct WPs using program execution feedback. FG utilises fuzz testing for approximately checking the validity and weakness of candidate WPs, this information is then fed back to the LLM as a means of context refinement. We demonstrate the effectiveness of our approach on a comprehensive benchmark set of deterministic array programs in Java. Our experiments indicate that LLMs are capable of producing viable candidate WPs, and that this ability can be practically enhanced through FG. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal on Software Tools for Technology Transfer is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Complementary Index |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: edb DbLabel: Complementary Index An: 194640828 RelevancyScore: 1082 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 1082.4189453125 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: LLMs and fuzzing in tandem: a new approach to automatically generating weakest preconditions. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22King%2C+Daragh%22">King, Daragh</searchLink><br /><searchLink fieldCode="AR" term="%22Koutavas%2C+Vasileios%22">Koutavas, Vasileios</searchLink><br /><searchLink fieldCode="AR" term="%22Kovács%2C+Laura%22">Kovács, Laura</searchLink> – Name: TitleSource Label: Source Group: Src Data: International Journal on Software Tools for Technology Transfer; Jun2026, Vol. 28 Issue 3, p317-328, 12p – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Software+verification%22">Software verification</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+software+testing%22">Computer software testing</searchLink><br /><searchLink fieldCode="DE" term="%22Java+programming+language%22">Java programming language</searchLink><br /><searchLink fieldCode="DE" term="%22Language+models%22">Language models</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+software%22">Computer software</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: The weakest precondition (WP) of a program describes the largest set of initial states from which all terminating executions of the program satisfy a given postcondition. The generation of WPs is an important task with practical applications in areas ranging from verification to run-time error checking. This paper proposes the combination of Large Language Models (LLMs) and fuzz testing for generating WPs. In pursuit of this goal, we introduce Fuzzing Guidance (FG); FG acts as a means of directing LLMs towards correct WPs using program execution feedback. FG utilises fuzz testing for approximately checking the validity and weakness of candidate WPs, this information is then fed back to the LLM as a means of context refinement. We demonstrate the effectiveness of our approach on a comprehensive benchmark set of deterministic array programs in Java. Our experiments indicate that LLMs are capable of producing viable candidate WPs, and that this ability can be practically enhanced through FG. [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Group: Ab Data: <i>Copyright of International Journal on Software Tools for Technology Transfer is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=194640828 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s10009-026-00844-2 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 12 StartPage: 317 Subjects: – SubjectFull: Software verification Type: general – SubjectFull: Computer software testing Type: general – SubjectFull: Java programming language Type: general – SubjectFull: Language models Type: general – SubjectFull: Computer software Type: general Titles: – TitleFull: LLMs and fuzzing in tandem: a new approach to automatically generating weakest preconditions. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: King, Daragh – PersonEntity: Name: NameFull: Koutavas, Vasileios – PersonEntity: Name: NameFull: Kovács, Laura IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 06 Text: Jun2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 14332779 Numbering: – Type: volume Value: 28 – Type: issue Value: 3 Titles: – TitleFull: International Journal on Software Tools for Technology Transfer Type: main |
| ResultId | 1 |