Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 32

The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.

SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents

Lin, Feng, Kim, Dong Jae, Chen, Tse-Hsun · 2025 · 2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE)

Abstract

Software process models are essential to facilitate collaboration and communication among software teams to solve complex development tasks. Inspired by these software engineering practices, we present FlowGen - a code generation framework that emulates software process models based on multiple Large Language Model (LLM) agents. We emulate three process models, FlowGenWaterfall, FlowGenTDD, and FlowGenScrum, by assigning LLM agents to embody roles (i.e., requirement engineer, architect, developer, tester, and scrum master) that correspond to everyday development activities and organize their communication patterns. The agents work collaboratively using chain-of-thought and prompt composition with continuous selfrefinement to improve the code quality. We use GPT3.5 as our underlying LLM and several baselines (RawGPT, CodeT, Reflexion) to evaluate code generation on four benchmarks: HumanEval, HumanEval-ET, MBPP, and MBPP-ET. Our findings show that FlowGenScrumexcels compared to other process models, achieving a Pass@1 of 75.2, 65.5, 82.5, and 56.7 in HumanEval, HumanEval-ET, MBPP, and MBPP-ET, respectively (an average of 15% improvement overRawGPT). Compared with other state-of-the-art techniques, FlowGenScrumachieves a higher Pass@1 in MBPP compared to CodeT, with both outperforming Reflexion. Notably, integrating CodeT into FlowGenScrumresulted in statistically significant improvements, achieving the highest Pass@1 scores. Our analysis also reveals that the development activities impacted code smell and exception handling differently, with design and code review adding more exception handling and reducing code smells. Finally, FlowGen models maintain stable Pass@1 scores across GPT3.5 versions and temperature values, highlighting the effectiveness of software process models in enhancing the quality and stability of LLM-generated code.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/icse55347.2025.00140

Cites

27 of 27 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 27 references

Research works printed but not linked: 34

  1. 10.1145/3643991.3645081 · DOI
  2. 2024, Repository & dataset
  3. Bassil, 2012, A simulation model for the waterfall software development life cycle, arXiv preprint
  4. Chen, 2021, Evaluating large language models trained on code, arXiv preprint
  5. 10.1007/978-1-4302-0439-8_11 · DOI
  6. 10.1145/3695991 · DOI
  7. Dong, 2023, Selfcollaboration code generation via chatgpt, arXiv preprint
  8. 10.1109/TSE.2004.35 · DOI
  9. Fowler, 2005, The new methodology
  10. Huang, 2023, Codecot and beyond: Learning to program and test like a developer, arXiv preprint
  11. Huang, 2023, Agentcoder: Multi-agent-based code generation with iterative testing and optimisation, arXiv preprint
  12. 10.1109/ICSE48619.2023.00194 · DOI · Paper page
  13. 10.1145/3690635 · DOI
  14. 10.1145/3597503.3623304 · DOI
  15. 10.1145/3597503.3639150 · DOI
  16. Madaan, 2024, Selfrefine: Iterative refinement with self-feedback, Advances in Neural Information Processing Systems, 36
  17. 10.1109/ICSE.2003.1201238 · DOI
  18. 2023, Chatgpt
  19. 2005, Built-in exceptions
  20. Ruiz, 2024, A novel approach for automatic program repair using round-trip translation with large language models, arXiv preprint
  21. 10.18653/v1/2023.emnlp-main.814 · DOI · Paper page
  22. 10.1109/QRS60937.2023.00031 · DOI
  23. 2024, Pylint
  24. 2024, What is devtestops?
  25. 10.1007/978-3-031-55642-5_4 · DOI · Paper page
  26. Xie, 2023, Chatunitest: a chatgpt-based automated unit test generation tool, arXiv preprint
  27. Xu, 2022, Alleviating the sample selection bias in few-shot learning by removing projection to the centroid, Advances in Neural Information Processing Systems, 35, 21073
  28. Xu, 2023, Exploring large language models for communication games: An empirical study on werewolf, arXiv preprint
  29. 10.1109/ICSM.2012.6405287 · DOI · Paper page
  30. Yetiştiren, 2023, Evaluating the code quality of ai-assisted code generation tools: An empirical study on github copilot, amazon codewhisperer, and chatgpt, arXiv preprint
  31. Yuan, 2023, Evaluating instructiontuned large language models on code comprehension and generation, arXiv preprint
  32. Yuan, 2023, No more manual tests? evaluating and improving ChatGPT for unit test generation, arXiv preprint
  33. 10.1109/TSE.2024.3364675 · DOI
  34. Zhong, 2024, Ldb: A large language model debugger via verifying runtime execution step-by-step, arXiv preprint

Cited by

See all 32

Metadata

Authors
Lin, F., Kim, D. J., & Chen, T.-H.
Affiliations
  • Concordia University,Software PErformance, Analysis, and Reliability (SPEAR) lab,Montreal,Canada
  • DePaul University,Chicago,USA
Venue
2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE)
Publisher
IEEE
Published
2025-04-26
Pages
1527-1539
Cited by
32
References
27

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents. https://app.cochat.ai/papers/10.1109/icse55347.2025.00140
The paper
Lin, F., Kim, D. J., & Chen, T.-H. (2025). SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents. 2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE). https://doi.org/10.1109/icse55347.2025.00140

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.