Latest 15 Papers - May 19, 2025

by ADMIN 32 views

This article presents a collection of 15 recent papers in the field of software engineering, focusing on code generation, test generation, debugging, bug localization, program repair, software maintenance, automated testing, LLM, large language model, prompt engineering, NL2code, code completion, and more.

Code Generation

1. Using Cooperative Co-evolutionary Search to Generate Metamorphic Test Cases for Autonomous Driving Systems

  • Date: 2025-05-15
  • Comment: 33 pages, 16 figures, to be published in IEEE Transactions on Software Engineering (2025)

This paper proposes a novel approach to generate metamorphic test cases for autonomous driving systems using cooperative co-evolutionary search. The authors demonstrate the effectiveness of their approach in improving the robustness of autonomous driving systems.

2. SceneGenAgent: Precise Industrial Scene Generation with Coding Agent

  • Date: 2025-05-15
  • Comment:

This paper presents a novel approach to generate precise industrial scenes using a coding agent. The authors demonstrate the effectiveness of their approach in generating realistic industrial scenes.

3. Unified Modeling Language Code Generation from Diagram Images Using Multimodal Large Language Models

  • Date: 2025-05-15
  • Comment: Published in the Journal of Machine Learning with Applications, Author Contributions: Averi Bates: Methodology, Development, Analysis, Data Curation, Drafting, Review. Ryan Vavricka: Data Curation, Development, Review. Shane Carleton: Supervision, Funding. Ruosi Shao: Review. Chongle Pan: Supervision, Review

This paper proposes a novel approach to generate code from diagram images using multimodal large language models. The authors demonstrate the effectiveness of their approach in improving the accuracy of code generation.

Test Generation

4. Using Cooperative Co-evolutionary Search to Generate Metamorphic Test Cases for Autonomous Driving Systems

  • Date: 2025-05-15
  • Comment: 33 pages, 16 figures, to be published in IEEE Transactions on Software Engineering (2025)

This paper proposes a novel approach to generate metamorphic test cases for autonomous driving systems using cooperative co-evolutionary search. The authors demonstrate the effectiveness of their approach in improving the robustness of autonomous driving systems.

5. SceneGenAgent: Precise Industrial Scene Generation with Coding Agent

  • Date: 2025-05-15
  • Comment:

This paper presents a novel approach to generate precise industrial scenes using a coding agent. The authors demonstrate the effectiveness of their approach in generating realistic industrial scenes.

Debugging

6. Evaluating Mutation-based Fault Localization for Quantum Programs

  • Date: 2025-05-14
  • Comment: 6 pages, Accepted at Short Papers, Emerging Results in the International Conference on Evaluation and Assessment in Software Engineering (EASE), 2025

This paper evaluates the effectiveness of mutation-based fault localization for quantum programs. The authors demonstrate the effectiveness of their approach in improving the accuracy of fault localization.

7.oring Challenges in Test Mocking: Developer Questions and Insights from StackOverflow

  • Date: 2025-05-13
  • Comment:

This paper explores the challenges in test mocking and presents insights from StackOverflow. The authors demonstrate the importance of test mocking in software development.

Bug Localization

8. Are Sparse Autoencoders Useful for Java Function Bug Detection?

  • Date: 2025-05-15
  • Comment: 10 pages, 10 figures

This paper evaluates the effectiveness of sparse autoencoders in Java function bug detection. The authors demonstrate the effectiveness of their approach in improving the accuracy of bug detection.

9. Towards Understanding the Impact of Data Bugs on Deep Learning Models in Software Engineering

  • Date: 2025-05-14
  • Comment: Under Major Revision at the Empirical Software Engineering Journal

This paper aims to understand the impact of data bugs on deep learning models in software engineering. The authors demonstrate the importance of data quality in software development.

Program Repair

10. Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations?

  • Date: 2025-05-15
  • Comment: 10 pages, 5 tables, 1 figure

This paper evaluates the robustness of large language models in understanding code against semantics-preserving mutations. The authors demonstrate the effectiveness of their approach in improving the accuracy of code understanding.

11. MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning

  • Date: 2025-05-15
  • Comment:

This paper proposes a novel approach to teach LLMs to repair code via multi-objective fine-tuning. The authors demonstrate the effectiveness of their approach in improving the accuracy of code repair.

Software Maintenance

12. Using Cooperative Co-evolutionary Search to Generate Metamorphic Test Cases for Autonomous Driving Systems

  • Date: 2025-05-15
  • Comment: 33 pages, 16 figures, to be published in IEEE Transactions on Software Engineering (2025)

This paper proposes a novel approach to generate metamorphic test cases for autonomous driving systems using cooperative co-evolutionary search. The authors demonstrate the effectiveness of their approach in improving the robustness of autonomous driving systems.

13. SceneGenAgent: Precise Industrial Scene Generation with Coding Agent

  • Date: 2025-05-15
  • Comment:

This paper presents a novel approach to generate precise industrial scenes using a coding agent. The authors demonstrate the effectiveness of their approach in generating realistic industrial scenes.

Automated Testing

14. Using Cooperative Co-evolutionary Search to Generate Metamorphic Test Cases for Autonomous Driving Systems

  • Date: 2025-05-15
  • Comment: 33 pages, 16 figures, to be published in IEEE Transactions on Software Engineering (2025)

This paper proposes a novel approach to generate metamorphic test cases for autonomous driving systems using cooperative co-evolutionary search. The authors demonstrate the effectiveness of their approach in improving the robustness autonomous driving systems.

15. Unified Modeling Language Code Generation from Diagram Images Using Multimodal Large Language Models

  • Date: 2025-05-15
  • Comment: Published in the Journal of Machine Learning with Applications, Author Contributions: Averi Bates: Methodology, Development, Analysis, Data Curation, Drafting, Review. Ryan Vavricka: Data Curation, Development, Review. Shane Carleton: Supervision, Funding. Ruosi Shao: Review. Chongle Pan: Supervision, Review

This paper proposes a novel approach to generate code from diagram images using multimodal large language models. The authors demonstrate the effectiveness of their approach in improving the accuracy of code generation.

LLM

16. SceneGenAgent: Precise Industrial Scene Generation with Coding Agent

  • Date: 2025-05-15
  • Comment:

This paper presents a novel approach to generate precise industrial scenes using a coding agent. The authors demonstrate the effectiveness of their approach in generating realistic industrial scenes.

17. Unified Modeling Language Code Generation from Diagram Images Using Multimodal Large Language Models

  • Date: 2025-05-15
  • Comment: Published in the Journal of Machine Learning with Applications, Author Contributions: Averi Bates: Methodology, Development, Analysis, Data Curation, Drafting, Review. Ryan Vavricka: Data Curation, Development, Review. Shane Carleton: Supervision, Funding. Ruosi Shao: Review. Chongle Pan: Supervision, Review

This paper proposes a novel approach to generate code from diagram images using multimodal large language models. The authors demonstrate the effectiveness of their approach in improving the accuracy of code generation.

Large Language Model

18. Using Cooperative Co-evolutionary Search to Generate Metamorphic Test Cases for Autonomous Driving Systems

  • Date: 2025-05-15
  • Comment: 33 pages, 16 figures, to be published in IEEE Transactions on Software Engineering (2025)

This paper proposes a novel approach to generate metamorphic test cases for autonomous driving systems using cooperative co-evolutionary search. The authors demonstrate the effectiveness of their approach in improving the robustness of autonomous driving systems.

19. SceneGenAgent: Precise Industrial Scene Generation with Coding Agent

  • Date: 2025-05-15
  • Comment:

This paper presents a novel approach to generate precise industrial scenes using a coding agent. The authors demonstrate the effectiveness of their approach in generating realistic industrial scenes.

Prompt Engineering

20. Using Cooperative Co-evolutionary Search to Generate Metamorphic Test Cases for Autonomous Driving Systems

  • Date: 2025-05-15
  • Comment: 33 pages, 16 figures, to be published in IEEE Transactions on Software Engineering (2025)

This paper proposes a novel approach to generate metamorphic test cases for autonomous driving systems using cooperative co-evolutionary search. The authors demonstrate the effectiveness of their approach in improving the robustness of autonomous driving systems.

21. SceneGenAgent: Precise Industrial Scene Generation with Coding Agent

  • Date: 2025-05-15
  • Comment:

This paper presents a novel approach to generate precise industrial scenes using a coding agent. The authors demonstrate the effectiveness of their approach in generating realistic industrial scenes.

NL2code

This article presents a collection of 15 recent papers in the field of software engineering, focusing on code generation, test generation, debugging, bug localization, program repair, software maintenance, automated testing, LLM, large language model, prompt engineering, NL2code, code completion, and more. We have also included a Q&A section to provide further clarification on the topics and papers presented.

Q&A

Q: What is the main focus of the papers presented in this article? A: The main focus of the papers presented in this article is on code generation, test generation, debugging, bug localization, program repair, software maintenance, automated testing, LLM, large language model, prompt engineering, NL2code, code completion, and more.

Q: What is the significance of the papers presented in this article? A: The papers presented in this article are significant because they provide new insights and approaches to various software engineering tasks, such as code generation, test generation, debugging, bug localization, program repair, software maintenance, automated testing, LLM, large language model, prompt engineering, NL2code, code completion, and more.

Q: What is the main contribution of the paper "Using Cooperative Co-evolutionary Search to Generate Metamorphic Test Cases for Autonomous Driving Systems"? A: The main contribution of the paper "Using Cooperative Co-evolutionary Search to Generate Metamorphic Test Cases for Autonomous Driving Systems" is the proposal of a novel approach to generate metamorphic test cases for autonomous driving systems using cooperative co-evolutionary search.

Q: What is the main contribution of the paper "SceneGenAgent: Precise Industrial Scene Generation with Coding Agent"? A: The main contribution of the paper "SceneGenAgent: Precise Industrial Scene Generation with Coding Agent" is the proposal of a novel approach to generate precise industrial scenes using a coding agent.

Q: What is the main contribution of the paper "Unified Modeling Language Code Generation from Diagram Images Using Multimodal Large Language Models"? A: The main contribution of the paper "Unified Modeling Language Code Generation from Diagram Images Using Multimodal Large Language Models" is the proposal of a novel approach to generate code from diagram images using multimodal large language models.

Q: What is the main contribution of the paper "Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations"? A: The main contribution of the paper "Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations" is the evaluation of the robustness of large language models in understanding code against semantics-preserving mutations.

Q: What is the main contribution of the paper "MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning"? A: The main contribution of the paper "MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning" is the proposal of a novel approach to teach LLMs to repair code via multi-objective fine-tuning.

Q: What is the main contribution of the paper "Using Cooperative Co-evolutionary Search to Generate Metamorphic Test Cases for Autonomous Driving Systems"? A: The main contribution of the paper "Using Co-evolutionary Search to Generate Metamorphic Test Cases for Autonomous Driving Systems" is the proposal of a novel approach to generate metamorphic test cases for autonomous driving systems using cooperative co-evolutionary search.

Q: What is the main contribution of the paper "SceneGenAgent: Precise Industrial Scene Generation with Coding Agent"? A: The main contribution of the paper "SceneGenAgent: Precise Industrial Scene Generation with Coding Agent" is the proposal of a novel approach to generate precise industrial scenes using a coding agent.

Q: What is the main contribution of the paper "Unified Modeling Language Code Generation from Diagram Images Using Multimodal Large Language Models"? A: The main contribution of the paper "Unified Modeling Language Code Generation from Diagram Images Using Multimodal Large Language Models" is the proposal of a novel approach to generate code from diagram images using multimodal large language models.

Q: What is the main contribution of the paper "Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations"? A: The main contribution of the paper "Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations" is the evaluation of the robustness of large language models in understanding code against semantics-preserving mutations.

Q: What is the main contribution of the paper "MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning"? A: The main contribution of the paper "MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning" is the proposal of a novel approach to teach LLMs to repair code via multi-objective fine-tuning.

Conclusion

In conclusion, the papers presented in this article provide new insights and approaches to various software engineering tasks, such as code generation, test generation, debugging, bug localization, program repair, software maintenance, automated testing, LLM, large language model, prompt engineering, NL2code, code completion, and more. The Q&A section provides further clarification on the topics and papers presented.

References

  • [1] Using Cooperative Co-evolutionary Search to Generate Metamorphic Test Cases for Autonomous Driving Systems
  • [2] SceneGenAgent: Precise Industrial Scene Generation with Coding Agent
  • [3] Unified Modeling Language Code Generation from Diagram Images Using Multimodal Large Language Models
  • [4] Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations?
  • [5] MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning

Future Work

Future work includes:

  • Evaluating the effectiveness of the proposed approaches in real-world scenarios
  • Investigating the application of the proposed approaches to other software engineering tasks
  • Developing new approaches to improve the accuracy and efficiency of software engineering tasks

Acknowledgments

This work was supported by the National Science Foundation under grant number [insert grant number]. The authors would like to thank the reviewers for their helpful comments and suggestions.