Code Digital Twin: Empowering LLMs with Tacit Knowledge for Complex Software Development Article Swipe

PDF

Xin Peng , Chong Wang , Mingwei Liu , Yiling Lou , Yijian Wu ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2503.07967

Recent advances in large language models (LLMs) have demonstrated strong capabilities in software engineering tasks, raising expectations of revolutionary productivity gains. However, enterprise software development is largely driven by incremental evolution, where challenges extend far beyond routine coding and depend critically on tacit knowledge, including design decisions at different levels and historical trade-offs. To achieve effective AI-powered support for complex software development, we should align emerging AI capabilities with the practical realities of enterprise development. To this end, we systematically identify challenges from both software and LLM perspectives. Alongside these challenges, we outline opportunities where AI and structured knowledge frameworks can enhance decision-making in tasks such as issue localization and impact analysis. To address these needs, we propose the Code Digital Twin, a living framework that models both the physical and conceptual layers of software, preserves tacit knowledge, and co-evolves with the codebase. By integrating hybrid knowledge representations, multi-stage extraction pipelines, incremental updates, LLM-empowered applications, and human-in-the-loop feedback, the Code Digital Twin transforms fragmented knowledge into explicit and actionable representations. Our vision positions it as a bridge between AI advancements and enterprise software realities, providing a concrete roadmap toward sustainable, intelligent, and resilient development and evolution of ultra-complex systems.

Related Topics

Handkerchief Code

Country Code Top-Level Domain

List Of Twin Peaks Characters

Bell Uh-1N Twin Huey

Central Bank Digital Currency

Code Talker

Psx (Digital Video Recorder)

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2503.07967
PDF: https://arxiv.org/pdf/2503.07967
OA Status: green
Cited By: 1
OpenAlex ID: https://openalex.org/W4414566824

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4414566824

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2503.07967

Digital Object Identifier
Title: Code Digital Twin: Empowering LLMs with Tacit Knowledge for Complex Software Development

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-03-11

Full publication date if available
Authors: Xin Peng, Chong Wang, Mingwei Liu, Yiling Lou, Yijian Wu

List of authors in order
Landing page: https://arxiv.org/abs/2503.07967

Publisher landing page
PDF URL: https://arxiv.org/pdf/2503.07967

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2503.07967

Direct OA link when available
Cited by: 1

Total citation count in OpenAlex
Citations by year (recent): 2025: 1

Per-year citation counts (last 5 years)

Full payload

id	https://openalex.org/W4414566824
doi	https://doi.org/10.48550/arxiv.2503.07967
ids.doi	https://doi.org/10.48550/arxiv.2503.07967
ids.openalex	https://openalex.org/W4414566824
fwci
type	preprint
title	Code Digital Twin: Empowering LLMs with Tacit Knowledge for Complex Software Development
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10538
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.8626999855041504
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1710
topics[0].subfield.display_name	Information Systems
topics[0].display_name	Data Mining Algorithms and Applications
topics[1].id	https://openalex.org/T11891
topics[1].field.id	https://openalex.org/fields/14
topics[1].field.display_name	Business, Management and Accounting
topics[1].score	0.8345999717712402
topics[1].domain.id	https://openalex.org/domains/2
topics[1].domain.display_name	Social Sciences
topics[1].subfield.id	https://openalex.org/subfields/1404
topics[1].subfield.display_name	Management Information Systems
topics[1].display_name	Big Data and Business Intelligence
topics[2].id	https://openalex.org/T11159
topics[2].field.id	https://openalex.org/fields/22
topics[2].field.display_name	Engineering
topics[2].score	0.8019000291824341
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/2209
topics[2].subfield.display_name	Industrial and Manufacturing Engineering
topics[2].display_name	Manufacturing Process and Optimization
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2503.07967
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/2503.07967
locations[0].version	submittedVersion
locations[0].raw_type
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/2503.07967
locations[1].id	doi:10.48550/arxiv.2503.07967
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	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
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.2503.07967
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5101854992
authorships[0].author.orcid	https://orcid.org/0000-0003-3376-2581
authorships[0].author.display_name	Xin Peng
authorships[0].author_position	first
authorships[0].raw_author_name	Peng, Xin
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5100329466
authorships[1].author.orcid	https://orcid.org/0000-0003-1424-6290
authorships[1].author.display_name	Chong Wang
authorships[1].author_position	middle
authorships[1].raw_author_name	Wang, Chong
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5102154339
authorships[2].author.orcid
authorships[2].author.display_name	Mingwei Liu
authorships[2].author_position	middle
authorships[2].raw_author_name	Liu, Mingwei
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5024354460
authorships[3].author.orcid	https://orcid.org/0000-0002-4066-3365
authorships[3].author.display_name	Yiling Lou
authorships[3].author_position	middle
authorships[3].raw_author_name	Lou, Yiling
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5006030692
authorships[4].author.orcid	https://orcid.org/0000-0001-9290-2068
authorships[4].author.display_name	Yijian Wu
authorships[4].author_position	last
authorships[4].raw_author_name	Wu, Yijian
authorships[4].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/2503.07967
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-09-27T00:00:00
display_name	Code Digital Twin: Empowering LLMs with Tacit Knowledge for Complex Software Development
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10538
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.8626999855041504
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1710
primary_topic.subfield.display_name	Information Systems
primary_topic.display_name	Data Mining Algorithms and Applications
cited_by_count	1
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	1
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2503.07967
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/2503.07967
best_oa_location.version	submittedVersion
best_oa_location.raw_type
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/2503.07967
primary_location.id	pmh:oai:arXiv.org:2503.07967
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/2503.07967
primary_location.version	submittedVersion
primary_location.raw_type
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/2503.07967
publication_date	2025-03-11
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	122, 175, 185
abstract_inverted_index.AI	66, 95, 178
abstract_inverted_index.By	143
abstract_inverted_index.To	53, 75, 112
abstract_inverted_index.as	106, 174
abstract_inverted_index.at	47
abstract_inverted_index.by	28
abstract_inverted_index.in	2, 11, 103
abstract_inverted_index.is	25
abstract_inverted_index.it	173
abstract_inverted_index.of	17, 72, 133, 196
abstract_inverted_index.on	41
abstract_inverted_index.we	62, 78, 91, 116
abstract_inverted_index.LLM	86
abstract_inverted_index.Our	170
abstract_inverted_index.and	38, 50, 85, 96, 109, 130, 138, 155, 167, 180, 191, 194
abstract_inverted_index.can	100
abstract_inverted_index.far	34
abstract_inverted_index.for	58
abstract_inverted_index.the	69, 118, 128, 141, 158
abstract_inverted_index.Code	119, 159
abstract_inverted_index.Twin	161
abstract_inverted_index.both	83, 127
abstract_inverted_index.end,	77
abstract_inverted_index.from	82
abstract_inverted_index.have	7
abstract_inverted_index.into	165
abstract_inverted_index.such	105
abstract_inverted_index.that	125
abstract_inverted_index.this	76
abstract_inverted_index.with	68, 140
abstract_inverted_index.Twin,	121
abstract_inverted_index.align	64
abstract_inverted_index.issue	107
abstract_inverted_index.large	3
abstract_inverted_index.tacit	42, 136
abstract_inverted_index.tasks	104
abstract_inverted_index.these	89, 114
abstract_inverted_index.where	31, 94
abstract_inverted_index.(LLMs)	6
abstract_inverted_index.Recent	0
abstract_inverted_index.beyond	35
abstract_inverted_index.bridge	176
abstract_inverted_index.coding	37
abstract_inverted_index.depend	39
abstract_inverted_index.design	45
abstract_inverted_index.driven	27
abstract_inverted_index.extend	33
abstract_inverted_index.gains.	20
abstract_inverted_index.hybrid	145
abstract_inverted_index.impact	110
abstract_inverted_index.layers	132
abstract_inverted_index.levels	49
abstract_inverted_index.living	123
abstract_inverted_index.models	5, 126
abstract_inverted_index.needs,	115
abstract_inverted_index.should	63
abstract_inverted_index.strong	9
abstract_inverted_index.tasks,	14
abstract_inverted_index.toward	188
abstract_inverted_index.vision	171
abstract_inverted_index.Digital	120, 160
abstract_inverted_index.achieve	54
abstract_inverted_index.address	113
abstract_inverted_index.between	177
abstract_inverted_index.complex	59
abstract_inverted_index.enhance	101
abstract_inverted_index.largely	26
abstract_inverted_index.outline	92
abstract_inverted_index.propose	117
abstract_inverted_index.raising	15
abstract_inverted_index.roadmap	187
abstract_inverted_index.routine	36
abstract_inverted_index.support	57
abstract_inverted_index.However,	21
abstract_inverted_index.advances	1
abstract_inverted_index.concrete	186
abstract_inverted_index.emerging	65
abstract_inverted_index.explicit	166
abstract_inverted_index.identify	80
abstract_inverted_index.language	4
abstract_inverted_index.physical	129
abstract_inverted_index.software	12, 23, 60, 84, 182
abstract_inverted_index.systems.	198
abstract_inverted_index.updates,	152
abstract_inverted_index.Alongside	88
abstract_inverted_index.analysis.	111
abstract_inverted_index.codebase.	142
abstract_inverted_index.decisions	46
abstract_inverted_index.different	48
abstract_inverted_index.effective	55
abstract_inverted_index.evolution	195
abstract_inverted_index.feedback,	157
abstract_inverted_index.framework	124
abstract_inverted_index.including	44
abstract_inverted_index.knowledge	98, 146, 164
abstract_inverted_index.positions	172
abstract_inverted_index.practical	70
abstract_inverted_index.preserves	135
abstract_inverted_index.providing	184
abstract_inverted_index.realities	71
abstract_inverted_index.resilient	192
abstract_inverted_index.software,	134
abstract_inverted_index.AI-powered	56
abstract_inverted_index.actionable	168
abstract_inverted_index.challenges	32, 81
abstract_inverted_index.co-evolves	139
abstract_inverted_index.conceptual	131
abstract_inverted_index.critically	40
abstract_inverted_index.enterprise	22, 73, 181
abstract_inverted_index.evolution,	30
abstract_inverted_index.extraction	149
abstract_inverted_index.fragmented	163
abstract_inverted_index.frameworks	99
abstract_inverted_index.historical	51
abstract_inverted_index.knowledge,	43, 137
abstract_inverted_index.pipelines,	150
abstract_inverted_index.realities,	183
abstract_inverted_index.structured	97
abstract_inverted_index.transforms	162
abstract_inverted_index.challenges,	90
abstract_inverted_index.development	24, 193
abstract_inverted_index.engineering	13
abstract_inverted_index.incremental	29, 151
abstract_inverted_index.integrating	144
abstract_inverted_index.multi-stage	148
abstract_inverted_index.trade-offs.	52
abstract_inverted_index.advancements	179
abstract_inverted_index.capabilities	10, 67
abstract_inverted_index.demonstrated	8
abstract_inverted_index.development,	61
abstract_inverted_index.development.	74
abstract_inverted_index.expectations	16
abstract_inverted_index.intelligent,	190
abstract_inverted_index.localization	108
abstract_inverted_index.productivity	19
abstract_inverted_index.sustainable,	189
abstract_inverted_index.LLM-empowered	153
abstract_inverted_index.applications,	154
abstract_inverted_index.opportunities	93
abstract_inverted_index.perspectives.	87
abstract_inverted_index.revolutionary	18
abstract_inverted_index.ultra-complex	197
abstract_inverted_index.systematically	79
abstract_inverted_index.decision-making	102
abstract_inverted_index.representations,	147
abstract_inverted_index.representations.	169
abstract_inverted_index.human-in-the-loop	156
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	5
citation_normalized_percentile