A Survey of LLM-based Automated Program Repair: Taxonomies, Design Paradigms, and Applications Article Swipe
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2506.23749
Large language models (LLMs) are reshaping automated program repair. We present a unified taxonomy that groups 62 recent LLM-based repair systems into four paradigms defined by parameter adaptation and control authority over the repair loop, and overlays two cross-cutting layers for retrieval and analysis augmentation. Prior surveys have either focused on classical software repair techniques, on LLMs in software engineering more broadly, or on subsets of LLM-based software repair, such as fine-tuning strategies or vulnerability repair. We complement these works by treating fine-tuning, prompting, procedural pipelines, and agentic frameworks as first-class paradigms and systematically mapping representative systems to each of these paradigms. We also consolidate evaluation practice on common benchmarks by recording benchmark scope, pass@k, and fault-localization assumptions to support a more meaningful comparison of reported success rates. We clarify trade-offs among paradigms in task alignment, deployment cost, controllability, and ability to repair multi-hunk or cross-file bugs. We discuss challenges in current LLM-based software repair and outline research directions. Our artifacts, including the representation papers and scripted survey pipeline, are publicly available at https://github.com/GLEAM-Lab/ProgramRepair.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2506.23749
- https://arxiv.org/pdf/2506.23749
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4416519743
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4416519743Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2506.23749Digital Object Identifier
- Title
-
A Survey of LLM-based Automated Program Repair: Taxonomies, Design Paradigms, and ApplicationsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-06-30Full publication date if available
- Authors
-
Boyang Yang, Zi-Jian Cai, Brian Le, Lingming Zhang, Tegawendé F. Bissyandé, Haoye TianList of authors in order
- Landing page
-
https://arxiv.org/abs/2506.23749Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2506.23749Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2506.23749Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4416519743 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2506.23749 |
| ids.doi | https://doi.org/10.48550/arxiv.2506.23749 |
| ids.openalex | https://openalex.org/W4416519743 |
| fwci | |
| type | preprint |
| title | A Survey of LLM-based Automated Program Repair: Taxonomies, Design Paradigms, and Applications |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2506.23749 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2506.23749 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2506.23749 |
| locations[1].id | doi:10.48550/arxiv.2506.23749 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2506.23749 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5101384214 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Boyang Yang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yang, Boyang |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5102982122 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-2378-5034 |
| authorships[1].author.display_name | Zi-Jian Cai |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Cai, Zijian |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5053379312 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-0830-4864 |
| authorships[2].author.display_name | Brian Le |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Le, Bach |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5043546718 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-5175-2702 |
| authorships[3].author.display_name | Lingming Zhang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Zhang, Lingming |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5082835974 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-7270-9869 |
| authorships[4].author.display_name | Tegawendé F. Bissyandé |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Bissyandé, Tegawendé F. |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5101397373 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-8049-3997 |
| authorships[5].author.display_name | Haoye Tian |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Tian, Haoye |
| authorships[5].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2506.23749 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | A Survey of LLM-based Automated Program Repair: Taxonomies, Design Paradigms, and Applications |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-12-06T23:10:59.065948 |
| primary_topic | |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2506.23749 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2506.23749 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2506.23749 |
| primary_location.id | pmh:oai:arXiv.org:2506.23749 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2506.23749 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2506.23749 |
| publication_date | 2025-06-30 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 11, 120 |
| abstract_inverted_index.62 | 16 |
| abstract_inverted_index.We | 9, 76, 102, 128, 147 |
| abstract_inverted_index.as | 70, 89 |
| abstract_inverted_index.at | 172 |
| abstract_inverted_index.by | 25, 80, 110 |
| abstract_inverted_index.in | 57, 133, 150 |
| abstract_inverted_index.of | 65, 99, 124 |
| abstract_inverted_index.on | 50, 55, 63, 107 |
| abstract_inverted_index.or | 62, 73, 144 |
| abstract_inverted_index.to | 97, 118, 141 |
| abstract_inverted_index.Our | 159 |
| abstract_inverted_index.and | 28, 35, 42, 86, 92, 115, 139, 155, 165 |
| abstract_inverted_index.are | 4, 169 |
| abstract_inverted_index.for | 40 |
| abstract_inverted_index.the | 32, 162 |
| abstract_inverted_index.two | 37 |
| abstract_inverted_index.LLMs | 56 |
| abstract_inverted_index.also | 103 |
| abstract_inverted_index.each | 98 |
| abstract_inverted_index.four | 22 |
| abstract_inverted_index.have | 47 |
| abstract_inverted_index.into | 21 |
| abstract_inverted_index.more | 60, 121 |
| abstract_inverted_index.over | 31 |
| abstract_inverted_index.such | 69 |
| abstract_inverted_index.task | 134 |
| abstract_inverted_index.that | 14 |
| abstract_inverted_index.Large | 0 |
| abstract_inverted_index.Prior | 45 |
| abstract_inverted_index.among | 131 |
| abstract_inverted_index.bugs. | 146 |
| abstract_inverted_index.cost, | 137 |
| abstract_inverted_index.loop, | 34 |
| abstract_inverted_index.these | 78, 100 |
| abstract_inverted_index.works | 79 |
| abstract_inverted_index.(LLMs) | 3 |
| abstract_inverted_index.common | 108 |
| abstract_inverted_index.either | 48 |
| abstract_inverted_index.groups | 15 |
| abstract_inverted_index.layers | 39 |
| abstract_inverted_index.models | 2 |
| abstract_inverted_index.papers | 164 |
| abstract_inverted_index.rates. | 127 |
| abstract_inverted_index.recent | 17 |
| abstract_inverted_index.repair | 19, 33, 53, 142, 154 |
| abstract_inverted_index.scope, | 113 |
| abstract_inverted_index.survey | 167 |
| abstract_inverted_index.ability | 140 |
| abstract_inverted_index.agentic | 87 |
| abstract_inverted_index.clarify | 129 |
| abstract_inverted_index.control | 29 |
| abstract_inverted_index.current | 151 |
| abstract_inverted_index.defined | 24 |
| abstract_inverted_index.discuss | 148 |
| abstract_inverted_index.focused | 49 |
| abstract_inverted_index.mapping | 94 |
| abstract_inverted_index.outline | 156 |
| abstract_inverted_index.pass@k, | 114 |
| abstract_inverted_index.present | 10 |
| abstract_inverted_index.program | 7 |
| abstract_inverted_index.repair, | 68 |
| abstract_inverted_index.repair. | 8, 75 |
| abstract_inverted_index.subsets | 64 |
| abstract_inverted_index.success | 126 |
| abstract_inverted_index.support | 119 |
| abstract_inverted_index.surveys | 46 |
| abstract_inverted_index.systems | 20, 96 |
| abstract_inverted_index.unified | 12 |
| abstract_inverted_index.analysis | 43 |
| abstract_inverted_index.broadly, | 61 |
| abstract_inverted_index.language | 1 |
| abstract_inverted_index.overlays | 36 |
| abstract_inverted_index.practice | 106 |
| abstract_inverted_index.publicly | 170 |
| abstract_inverted_index.reported | 125 |
| abstract_inverted_index.research | 157 |
| abstract_inverted_index.scripted | 166 |
| abstract_inverted_index.software | 52, 58, 67, 153 |
| abstract_inverted_index.taxonomy | 13 |
| abstract_inverted_index.treating | 81 |
| abstract_inverted_index.LLM-based | 18, 66, 152 |
| abstract_inverted_index.authority | 30 |
| abstract_inverted_index.automated | 6 |
| abstract_inverted_index.available | 171 |
| abstract_inverted_index.benchmark | 112 |
| abstract_inverted_index.classical | 51 |
| abstract_inverted_index.including | 161 |
| abstract_inverted_index.paradigms | 23, 91, 132 |
| abstract_inverted_index.parameter | 26 |
| abstract_inverted_index.pipeline, | 168 |
| abstract_inverted_index.recording | 111 |
| abstract_inverted_index.reshaping | 5 |
| abstract_inverted_index.retrieval | 41 |
| abstract_inverted_index.adaptation | 27 |
| abstract_inverted_index.alignment, | 135 |
| abstract_inverted_index.artifacts, | 160 |
| abstract_inverted_index.benchmarks | 109 |
| abstract_inverted_index.challenges | 149 |
| abstract_inverted_index.comparison | 123 |
| abstract_inverted_index.complement | 77 |
| abstract_inverted_index.cross-file | 145 |
| abstract_inverted_index.deployment | 136 |
| abstract_inverted_index.evaluation | 105 |
| abstract_inverted_index.frameworks | 88 |
| abstract_inverted_index.meaningful | 122 |
| abstract_inverted_index.multi-hunk | 143 |
| abstract_inverted_index.paradigms. | 101 |
| abstract_inverted_index.pipelines, | 85 |
| abstract_inverted_index.procedural | 84 |
| abstract_inverted_index.prompting, | 83 |
| abstract_inverted_index.strategies | 72 |
| abstract_inverted_index.trade-offs | 130 |
| abstract_inverted_index.assumptions | 117 |
| abstract_inverted_index.consolidate | 104 |
| abstract_inverted_index.directions. | 158 |
| abstract_inverted_index.engineering | 59 |
| abstract_inverted_index.fine-tuning | 71 |
| abstract_inverted_index.first-class | 90 |
| abstract_inverted_index.techniques, | 54 |
| abstract_inverted_index.fine-tuning, | 82 |
| abstract_inverted_index.augmentation. | 44 |
| abstract_inverted_index.cross-cutting | 38 |
| abstract_inverted_index.vulnerability | 74 |
| abstract_inverted_index.representation | 163 |
| abstract_inverted_index.representative | 95 |
| abstract_inverted_index.systematically | 93 |
| abstract_inverted_index.controllability, | 138 |
| abstract_inverted_index.fault-localization | 116 |
| abstract_inverted_index.https://github.com/GLEAM-Lab/ProgramRepair. | 173 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |