Coding Agents: A Comprehensive Survey of Automated Bug Fixing Systems and Benchmarks

One of the trickiest problems in software engineering is automating software issue fixes, which calls for a thorough comprehension of contextual relationships, code semantics, and dynamic debugging techniques. The development of automatic program repair (APR) is examined in this survey, which traces...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings (International Conference on Communication Systems and Network Technologies Online) s. 680 - 686
Hlavní autori: Puvvadi, Meghana, Arava, Sai Kumar, Santoria, Adarsh, Chennupati, Sesha Sai Prasanna, Puvvadi, Harsha Vardhan
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 07.03.2025
Predmet:
ISSN:2473-5655
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract One of the trickiest problems in software engineering is automating software issue fixes, which calls for a thorough comprehension of contextual relationships, code semantics, and dynamic debugging techniques. The development of automatic program repair (APR) is examined in this survey, which traces a path from early template and constraint-based approaches to more recent developments powered by large language models (LLMs). Three main paradigms are compared here: retrieval-augmented approaches that integrate external knowledge sources, agent-based systems that use multi-agent frameworks, and agentless systems that use simplified repair pipelines. Real-world benchmarks that mimic actual engineering workflows and repository-level difficulties, such as SWE-bench, CODEAGENT-BENCH, and CodeRAG-Bench, are used to assess these cutting-edge technologies. This study demonstrates how agentic, agentless, and retrieval-augmented systems use LLMs to achieve previously unheard-of precision and scalability by following the shift from localized, single-file solutions to solving complicated, multi-file, and repository-wide difficulties. According to our findings, while complex agent architectures have potential, straightforward test-time scaling frequently produces better outcomes, especially when paired with containerized environments that allow for parallel exploration. Additionally, the survey looks at industrial applications, emphasizing effective connections with quality assurance and DevOps procedures. In order to further the development of more resilient and flexible APR frameworks that blend in perfectly with contemporary software engineering practices, we conclude by highlighting important issues in context handling and validation and suggesting future research directions in improved contextual models, human-AI collaboration, and multi-modal debugging systems.
AbstractList One of the trickiest problems in software engineering is automating software issue fixes, which calls for a thorough comprehension of contextual relationships, code semantics, and dynamic debugging techniques. The development of automatic program repair (APR) is examined in this survey, which traces a path from early template and constraint-based approaches to more recent developments powered by large language models (LLMs). Three main paradigms are compared here: retrieval-augmented approaches that integrate external knowledge sources, agent-based systems that use multi-agent frameworks, and agentless systems that use simplified repair pipelines. Real-world benchmarks that mimic actual engineering workflows and repository-level difficulties, such as SWE-bench, CODEAGENT-BENCH, and CodeRAG-Bench, are used to assess these cutting-edge technologies. This study demonstrates how agentic, agentless, and retrieval-augmented systems use LLMs to achieve previously unheard-of precision and scalability by following the shift from localized, single-file solutions to solving complicated, multi-file, and repository-wide difficulties. According to our findings, while complex agent architectures have potential, straightforward test-time scaling frequently produces better outcomes, especially when paired with containerized environments that allow for parallel exploration. Additionally, the survey looks at industrial applications, emphasizing effective connections with quality assurance and DevOps procedures. In order to further the development of more resilient and flexible APR frameworks that blend in perfectly with contemporary software engineering practices, we conclude by highlighting important issues in context handling and validation and suggesting future research directions in improved contextual models, human-AI collaboration, and multi-modal debugging systems.
Author Puvvadi, Meghana
Puvvadi, Harsha Vardhan
Arava, Sai Kumar
Chennupati, Sesha Sai Prasanna
Santoria, Adarsh
Author_xml – sequence: 1
  givenname: Meghana
  surname: Puvvadi
  fullname: Puvvadi, Meghana
  email: mpuvvadi@adobe.com
  organization: Head of Inference Platform,Adobe Systems,San Jose,USA
– sequence: 2
  givenname: Sai Kumar
  surname: Arava
  fullname: Arava, Sai Kumar
  email: arakumar@adobe.com
  organization: Senior Machine Learning Manager,Adobe Systems,San Jose,USA
– sequence: 3
  givenname: Adarsh
  surname: Santoria
  fullname: Santoria, Adarsh
  email: b21176@students.iitmandi.ac.in
  organization: IIT Mandi,Dept. of Electrical Engineering,Mandi,India
– sequence: 4
  givenname: Sesha Sai Prasanna
  surname: Chennupati
  fullname: Chennupati, Sesha Sai Prasanna
  email: Schennupati@rippling.com
  organization: Rippling Senior Software Engineer,San Jose,USA
– sequence: 5
  givenname: Harsha Vardhan
  surname: Puvvadi
  fullname: Puvvadi, Harsha Vardhan
  email: H.Puvvadi@shell.com
  organization: Associate QA Specialist,Shell India Markets Pvt. Ltd,Bangalore,India
BookMark eNo1kN9OgzAUxqvRxDn3Bib2BZjtOZRS75BsarLoBdwvMA5bVcpCYZG3F6Nefckv35_ku2YXrnXE2J0USymFuU-z1zwKY9BLEKCWE4piDfEZWxhtYkSpUBpU52wGocZARUpdsYX370IIBCkjAzOWp21l3Z4ne3K9f-AJT9vm2NGBnLcn4tnQnWjkbc2ToW-boqeKPw57vrZfP7Fs9D01nhduwuR2h6boPvwNu6yLT0-LP52zfL3K0-dg8_b0kiabwBrsA9JkEMpS1jtERVVtkLRQVVxEJZDZgZGgNalSgjHl5ICKUAsIQ10XtdQ4Z7e_tZaItsfOTuPj9v8H_AbGFFPy
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/CSNT64827.2025.10968728
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9798331531935
EISSN 2473-5655
EndPage 686
ExternalDocumentID 10968728
Genre orig-research
GroupedDBID 6IE
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-i93t-e7e932bb1fc335edf93e705d8a6b2e9c291277e5b1299b35e2de3702447faf173
IEDL.DBID RIE
IngestDate Wed Apr 30 05:50:37 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-e7e932bb1fc335edf93e705d8a6b2e9c291277e5b1299b35e2de3702447faf173
PageCount 7
ParticipantIDs ieee_primary_10968728
PublicationCentury 2000
PublicationDate 2025-March-7
PublicationDateYYYYMMDD 2025-03-07
PublicationDate_xml – month: 03
  year: 2025
  text: 2025-March-7
  day: 07
PublicationDecade 2020
PublicationTitle Proceedings (International Conference on Communication Systems and Network Technologies Online)
PublicationTitleAbbrev CSNT
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211692
Score 1.9014181
Snippet One of the trickiest problems in software engineering is automating software issue fixes, which calls for a thorough comprehension of contextual relationships,...
SourceID ieee
SourceType Publisher
StartPage 680
SubjectTerms Agent-Based Models
AI in Software Development
Automated Program Repair
Benchmark testing
Context modeling
Context-Aware Debugging
Debugging
Debugging Benchmarks
Large language models
Maintenance engineering
Multi-Agent Systems
Scalability
Semantics
Software
Software engineering
Software Engineering Automation
Surveys
Title Coding Agents: A Comprehensive Survey of Automated Bug Fixing Systems and Benchmarks
URI https://ieeexplore.ieee.org/document/10968728
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDI5g4gAXXkO8lQPXjjZp44bbmJg4TZPWw25T0jpsQrSoayf49yRdN-DAgVvkOEpkK7Kd-LMJueOC-9pk3PMVBy9kRns6Re2lvjSgjbE-rGqaTcBoFE-nctyC1RssDCI2yWfYc8PmLz8r0to9ldkbLkUMLN4luwBiDdbaPqhwG8oIydocLst6P5iMEuHKXNowkEW9zepffVQaMzI8_OcBjkj3G5BHx1tTc0x2MD8hBz9qCZ6SZFC4Odp3WKnlA-1Td9VLnK8z1OmkLlf4SQtD-3VVWD8VM_pYv9Dh4sMtayuXU5Vbst1v_qbK12WXJMOnZPDstS0TvIXklYeA1h_TOjAp5xFmRnIEP8piJTRDmTIZMACMtLXyUlsOliEHa6ZDMMoEwM9IJy9yPCc0k1HKYxUA2mnQgUYRgpKMSWZCFOKCdJ18Zu_rohizjWgu_6BfkX2nhSZ9C65JpyprvCF76apaLMvbRpVf6FafrQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDI5gIAEXXkO8yYFroU3apOE2JqYhxjRpPew2Ja3DJkSLunaCf0_SdQMOHLhFjqNEtiLbiT8boWvKqKt0Qh1XUu74RCtHxaCc2BWaK62NDyurZhO83w9HIzGoweoVFgYAquQzuLHD6i8_yeLSPpWZGy5YyEm4jjYC3yfuAq61elKhJphhgtRZXIb5tj3sR8wWujSBIAlulut_dVKpDEln959H2EPNb0geHqyMzT5ag_QA7fyoJniIonZm53DLoqVmd7iF7WXPYbLIUcfDMp_DJ840bpVFZjxVSPB9-YI70w-7rK5djmVqyGa_yZvMX2dNFHUeonbXqZsmOFNBCwc4GI9MKU_HlAaQaEGBu0ESSqYIiJgIj3AOgTJ2XijDQRKg3Bhqn2upPU6PUCPNUjhGOBFBTEPpcTDTXHkKmM-lIEQQ7QNjJ6hp5TN-X5TFGC9Fc_oH_QptdaPn3rj32H86Q9tWI1UyFz9HjSIv4QJtxvNiOssvK7V-AWecovQ
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+%28International+Conference+on+Communication+Systems+and+Network+Technologies+Online%29&rft.atitle=Coding+Agents%3A+A+Comprehensive+Survey+of+Automated+Bug+Fixing+Systems+and+Benchmarks&rft.au=Puvvadi%2C+Meghana&rft.au=Arava%2C+Sai+Kumar&rft.au=Santoria%2C+Adarsh&rft.au=Chennupati%2C+Sesha+Sai+Prasanna&rft.date=2025-03-07&rft.pub=IEEE&rft.eissn=2473-5655&rft.spage=680&rft.epage=686&rft_id=info:doi/10.1109%2FCSNT64827.2025.10968728&rft.externalDocID=10968728