mlsanityData to 14 Oct 2026

Are LLMs Correctly Integrated into Software Systems?

arXiv 2407.05138 ↗First posted 6 Jul 2024cs.SE cs.AIcited by 15

On the map: Retrieval-augmented generation → RAG for code

Abstract (arXiv)

Large language models (LLMs) provide effective solutions in various application scenarios, with the support of retrieval-augmented generation (RAG). However, developers face challenges in integrating LLM and RAG into software systems, due to lacking interface specifications, various requirements from software context, and complicated system management. In this paper, we have conducted a comprehensive study of 100 open-source applications that incorporate LLMs with RAG support, and identified 18 defect patterns. Our study reveals that 77% of these applications contain more than three types of integration defects that degrade software functionality, efficiency, and security. Guided by our study, we propose systematic guidelines for resolving these defects in software life cycle. We also construct an open-source defect library Hydrangea.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in RAG for code, one of 15 directions in Retrieval-augmented generation. Builds on 51 of its 99 references that are in the map. First posted on arXiv 6 Jul 2024.

Builds on

51 of 99 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair12 Sep
  2. 2021Retrieval Augmented Code Generation and Summarization26 Aug

Other references · 49

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  5. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  7. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  8. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
  9. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 733
  10. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  11. 2023A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPTcited by 619
  12. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 518
37 more
  1. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 462
  2. 2023Large Language Models for Software Engineering: A Systematic Literature Reviewcited by 399
  3. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 387
  4. 2023RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generationcited by 367
  5. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  6. 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 311
  7. 2024TrustLLM: Trustworthiness in Large Language Modelscited by 285
  8. 2017DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Carscited by 251
  9. 2023MathPrompter: Mathematical Reasoning using Large Language Modelscited by 236
  10. 2023Large Language Models as Commonsense Knowledge for Large-Scale Task Planningcited by 231
  11. 2022DocPrompting: Generating Code by Retrieving the Docscited by 153
  12. 2018DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systemscited by 147
  13. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 139
  14. 2018Guiding Deep Learning System Testing using Surprise Adequacycited by 124
  15. 2023Evaluating Open-Domain Question Answering in the Era of Large Language Modelscited by 111
  16. 2024Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Codecited by 107
  17. 2023LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Modelscited by 101
  18. 2019Taxonomy of Real Faults in Deep Learning Systemscited by 90
  19. 2023Fuzz4All: Universal Fuzzing with Large Language Modelscited by 88
  20. 2022Automated Repair of Programs from Large Language Modelscited by 71
  21. 2018A First Look at Deep Learning Apps on Smartphonescited by 47
  22. 2024CYCLE: Learning to Self-Refine the Code Generationcited by 42
  23. 2024PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makerscited by 42
  24. 2023Prompting Is All You Need: Automated Android Bug Replay with Large Language Modelscited by 40
  25. 2023Demystifying RCE Vulnerabilities in LLM-Integrated Appscited by 37
  26. 2019An Empirical Study towards Characterizing Deep Learning Development and Deployment across Different Frameworks and Platformscited by 35
  27. 2023Prompt Packer: Deceiving LLMs through Compositional Instruction with Hidden Attackscited by 35
  28. 2022NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilerscited by 30
  29. 2023DB-GPT: Empowering Database Interactions with Private Large Language Modelscited by 27
  30. 2021DocTer: Documentation Guided Fuzzing for Testing Deep Learning API Functionscited by 22
  31. 2021An Empirical Study on Deployment Faults of Deep Learning Based Mobile Applicationscited by 20
  32. 2021Self-Checking Deep Neural Networks in Deploymentcited by 18
  33. 2021PatchCensor: Patch Robustness Certification for Transformers via Exhaustive Testingcited by 12
  34. 2021Efficient Online ML API Selection for Multi-Label Classification Taskscited by 11
  35. 2023Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoningcited by 11
  36. 2021ArchRepair: Block-Level Architecture-Oriented Repairing for Deep Neural Networkscited by 7
  37. 2022Cost Effective MLaaS Federation: A Combinatorial Reinforcement Learning Approachcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 7; 2026: 7.

15 papers.

Sort:

By area:

  1. 2025SWE-Exp: Experience-Driven Software Issue Resolutioncited by 65
  2. 2025Agent READMEs: An Empirical Study of Context Files for Agentic Codingcited by 23
  3. 2025Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errorscited by 14
  4. 2025Can Agents Fix Agent Issues?cited by 9
  5. 2025A Taxonomy of Prompt Defects in LLM Systemscited by 8
  6. 2024Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systemscited by 7
  7. 2026Why Does the LLM Stop Computing: An Empirical Study of User-Reported Failures in Open-Source LLMscited by 3
  8. 2026LIDL: LLM Integration Defect Localization via Knowledge Graph-Enhanced Multi-Agent Analysiscited by 2
  9. 2025A Research Roadmap for Augmenting Software Engineering Processes and Software Products with Generative AIcited by 1
  10. 2026Key Considerations for Domain Expert Involvement in LLM Design and Evaluation: An Ethnographic Studycited by 1
  11. 2025Specification and Detection of LLM Code Smellscited by 0
  12. 2026MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repaircited by 0
3 more
  1. 2026LLM Code Smells: A Taxonomy and Detection Approachcited by 0
  2. 2026AgentBug-Smith: Automatically Reproducing Real-World Harness Bugs in Agentic Systemscited by 0
  3. 2026Configuring RAG Systems: What Breaks, Where Originates, and How to Fixcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025When LLMs Meet API Documentation: Can Retrieval Augmentation Aid Code Generation Just as It Helps Developers?
  2. 2025WIP: Leveraging LLMs for Enforcing Design Principles in Student Code: Analysis of Prompting Strategies and RAG ↗
  3. 2024Evaluating the Efficacy of Open-Source LLMs in Enterprise-Specific RAG Systems: A Comparative Study of Performance and Scalability
  4. 2024Themes of Building LLM-based Applications for Production: A Practitioner's View ↗
  5. 2025Holistic Evaluation of State-of-the-Art LLMs for Code Generation
  6. 2024A Methodology for Evaluating RAG Systems: A Case Study On Configuration Dependency Validation
  7. 2024A RAG Method for Source Code Inquiry Tailored to Long-Context LLMs
  8. 2026Enhancing Large Language Models with Retrieval Augmented Generation for Software Testing and Inspection Automation