Academic Journal

Optimizing Context and Cost in LLM‐Based Unit Test Generation: A Study on External Dependency Retrieval Strategies.

Bibliographic Details
Title: Optimizing Context and Cost in LLM‐Based Unit Test Generation: A Study on External Dependency Retrieval Strategies.
Authors: Ferrer, Javier1 (AUTHOR) jferrer@uma.es, Chicano, Francisco1 (AUTHOR)
Source: Expert Systems. Oct2026, Vol. 43 Issue 10, p1-21. 21p.
Subject Terms: *Mathematical optimization, Prompt engineering, Computer software testing
Abstract: While Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, their effectiveness in unit testing is often constrained by insufficient context regarding external dependencies. This limitation is particularly pronounced in industrial settings, where proprietary code remains opaque to the model. To address this challenge, we present a systematic empirical study of multiple strategies for context enrichment and optimization in LLM‐based unit test generation, conducted on seven diverse projects (three open‐source and four proprietary industrial systems), encompassing 261 distinct methods. By evaluating seven implementations (ranging from basic prompts to optimized context reduction strategies) across 10 independent runs, we analysed a total of 28,710 test suites. Our results demonstrate that combining prompt engineering with external dependency retrieval achieves an average branch coverage increase of 11.52 percentage points on industrial software over the baseline, with statistically significant improvements across all competing implementations. Beyond coverage, richer context substantially reduces generation‐repair iterations, cutting median execution time by 51.3% in industrial projects. We further show that reducing external dependencies to method signatures alone decreases input token consumption by up to 46.6% (25.4% in industrial projects) while fully preserving the coverage and efficiency gains of the complete retrieval approach. To confirm that these benefits are not tied to a specific model, we replicate the core comparison across three LLM backends from different families, obtaining a consistent, statistically significant coverage improvement on industrial code in every case. These findings establish this optimized context strategy as a cost‐effective solution for scalable, industrial‐grade automated test generation. [ABSTRACT FROM AUTHOR]
Copyright of Expert Systems is the property of Wiley-Blackwell 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: Business Source Index
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:bsx&genre=article&issn=02664720&ISBN=&volume=43&issue=10&date=20261001&spage=1&pages=1-21&title=Expert Systems&atitle=Optimizing%20Context%20and%20Cost%20in%20LLM%E2%80%90Based%20Unit%20Test%20Generation%3A%20A%20Study%20on%20External%20Dependency%20Retrieval%20Strategies.&aulast=Ferrer%2C%20Javier&id=DOI:10.1111/exsy.70401
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: bsx
DbLabel: Business Source Index
An: 197136948
RelevancyScore: 1418
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1417.99206542969
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Optimizing Context and Cost in LLM‐Based Unit Test Generation: A Study on External Dependency Retrieval Strategies.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Ferrer%2C+Javier%22">Ferrer, Javier</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> jferrer@uma.es</i><br /><searchLink fieldCode="AR" term="%22Chicano%2C+Francisco%22">Chicano, Francisco</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Expert+Systems%22">Expert Systems</searchLink>. Oct2026, Vol. 43 Issue 10, p1-21. 21p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Mathematical+optimization%22">Mathematical optimization</searchLink><br /><searchLink fieldCode="DE" term="%22Prompt+engineering%22">Prompt engineering</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+software+testing%22">Computer software testing</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: While Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, their effectiveness in unit testing is often constrained by insufficient context regarding external dependencies. This limitation is particularly pronounced in industrial settings, where proprietary code remains opaque to the model. To address this challenge, we present a systematic empirical study of multiple strategies for context enrichment and optimization in LLM‐based unit test generation, conducted on seven diverse projects (three open‐source and four proprietary industrial systems), encompassing 261 distinct methods. By evaluating seven implementations (ranging from basic prompts to optimized context reduction strategies) across 10 independent runs, we analysed a total of 28,710 test suites. Our results demonstrate that combining prompt engineering with external dependency retrieval achieves an average branch coverage increase of 11.52 percentage points on industrial software over the baseline, with statistically significant improvements across all competing implementations. Beyond coverage, richer context substantially reduces generation‐repair iterations, cutting median execution time by 51.3% in industrial projects. We further show that reducing external dependencies to method signatures alone decreases input token consumption by up to 46.6% (25.4% in industrial projects) while fully preserving the coverage and efficiency gains of the complete retrieval approach. To confirm that these benefits are not tied to a specific model, we replicate the core comparison across three LLM backends from different families, obtaining a consistent, statistically significant coverage improvement on industrial code in every case. These findings establish this optimized context strategy as a cost‐effective solution for scalable, industrial‐grade automated test generation. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Expert Systems is the property of Wiley-Blackwell 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=bsx&AN=197136948
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1111/exsy.70401
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 21
        StartPage: 1
    Subjects:
      – SubjectFull: Mathematical optimization
        Type: general
      – SubjectFull: Prompt engineering
        Type: general
      – SubjectFull: Computer software testing
        Type: general
    Titles:
      – TitleFull: Optimizing Context and Cost in LLM‐Based Unit Test Generation: A Study on External Dependency Retrieval Strategies.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Ferrer, Javier
      – PersonEntity:
          Name:
            NameFull: Chicano, Francisco
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: Oct2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 02664720
          Numbering:
            – Type: volume
              Value: 43
            – Type: issue
              Value: 10
          Titles:
            – TitleFull: Expert Systems
              Type: main
ResultId 1