Research on Hybrid Collaborative Development Model Based on Multi-Dimensional Behavioral Information
Source abstract
Abstract
This paper aims to propose a hybrid collaborative development model based on multi-dimensional behavioral information (HCDMB) to deal with systemic problems in modern software engineering, such as the low efficiency of cross-stage collaboration, the fragmentation of the intelligent tool chain, and the imperfect human–machine collaboration mechanism. This paper focuses on the stages of requirements analysis, software development, software testing and software operation and maintenance in the process of software development. By integrating the multi-dimensional characteristics of the development behavior track, collaboration interaction record and product application data in the process of project promotion, the mixture of experts (MoE) model is introduced to break through the rigid constraints of the traditional tool chain. Reinforcement learning combined with human feedback is used to optimize the MoE dynamic routing mechanism. At the same time, the few-shot context learning method is used to build different expert models, which further improve the reasoning efficiency and knowledge transfer ability of the system in different scenarios. The HCDMB model proposed in this paper can be viewed as an important breakthrough in the software engineering collaboration paradigm, so as to provide innovative solutions to the many problems faced by dynamic requirements and diverse scenarios based on artificial intelligence technology in the field of software engineering involving different project personnel.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Collaboration in agile enterprises
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Software Engineering, Chengdu University of Information Technology, Chengdu 610225, China
Funding
National Key Research and Development Program of China
References (46)
Show source-provided references
1. DevOps10.1109/MS.2016.68 ↗
2. Xie, T. (2018, January 9–11). Intelligent software engineering: Synergy between AI and software engineering. Proceedings of the 11th Innovations in Software Engineering Conference, Hyderabad, India.10.1145/3172871.3172891 ↗
3. Software engineering for AI-based systems: A survey
4. What is really different in engineering AI-enabled systems?
5. Davis, A.M. (1990). Software Requirements: Analysis and Specification, Prentice Hall Press.
6. Agile requirements engineering practices and challenges: An empirical study10.1111/j.1365-2575.2007.00259.x ↗
7. BET-BiLSTM Model: A Robust Solution for Automated Requirements Classification10.1002/smr.70012 ↗
8. de Araújo, A.F., and Marcacini, R.M. (2021, January 22–26). Re-bert: Automatic extraction of software requirements from app reviews using bert language model. Proceedings of the 36th Annual ACM Symposium on Applied Computing, Virtual.10.1145/3412841.3442006 ↗
9. Koroteev, M.V. (2021). BERT: A review of applications in natural language processing and understanding. arXiv.
10. Hurst, A., Lerer, A., Goucher, A.P., Perelman, A., Ramesh, A., Clark, A., Ostrow, A.J., Welihinda, A., Hayes, A., and Radford, A. (2024). Gpt-4o system card. arXiv.
11. Bai, S., Chen, K., Liu, X., Wang, J., Ge, W., Song, S., Dang, K., Wang, P., Wang, S., and Tang, J. (2025). Qwen2. 5-vl technical report. arXiv.
12. Using Large Language Models in Software Requirements Analysis10.55214/25768484.v9i3.5357 ↗
13. Marques, N., Silva, R.R., and Bernardino, J. (2024). Using chatgpt in software requirements engineering: A comprehensive review. Future Internet, 16.10.3390/fi16060180 ↗
14. Jin, H., Huang, L., Cai, H., Yan, J., Li, B., and Chen, H. (2024). From llms to llm-based agents for software engineering: A survey of current, challenges and future. arXiv.
15. Software engineering methodologies: A review of the waterfall model and object-oriented approach
16. Machine learning techniques for code smell detection: A systematic literature review and meta-analysis10.1016/j.infsof.2018.12.009 ↗
17. Sun, H., Xu, Z.F., and Li, X. (2023, January 14–16). Code Recommendation Based on Deep Learning. Proceedings of the 2023 12th International Conference of Information and Communication Technology (ICTech), Wuhan, China.10.1109/ICTech58362.2023.00041 ↗
18. Zhang, B., Liang, P., Zhou, X., Ahmad, A., and Waseem, M. (2023). Practices and challenges of using github copilot: An empirical study. arXiv.10.18293/SEKE2023-077 ↗
19. Drain, D., Clement, C.B., Serrato, G., and Sundaresan, N. (2021). Deepdebug: Fixing python bugs using stack traces, backtranslation, and code skeletons. arXiv.
20. Nam, D., Macvean, A., Hellendoorn, V., Vasilescu, B., and Myers, B. (2024, January 14–20). Using an llm to help with code understanding. Proceedings of the IEEE/ACM 46th International Conference on Software Engineering, Lisbon, Portugal.10.1145/3597503.3639187 ↗
21. Ammann, P., and Offutt, J. (2016). Introduction to Software Testing, Cambridge University Press.10.1017/9781316771273 ↗
22. Orso, A., and Rothermel, G. (2014). Software testing: A research travelogue (2000–2014). Future of Software Engineering Proceedings, Association for Computing Machinery.10.1145/2593882.2593885 ↗
23. The automatic generation of software test data sets using adaptive search techniques
24. Zhu, Y., Guo, X., Okamura, H., and Dohi, T. (2024). Automated Software Test Input Generation with Diffusion Models. International Symposium on Software Fault Prevention, Verification, and Validation, Springer Nature.10.1007/978-981-96-1621-3_3 ↗
25. Software testing with large language models: Survey, landscape, and vision10.1109/TSE.2024.3368208 ↗
26. Reinforcement learning
27. The role of Reinforcement Learning in software testing10.1016/j.infsof.2023.107325 ↗
28. Adaptive mixtures of local experts10.1162/neco.1991.3.1.79 ↗
29. Shazeer, N., Mirhoseini, A., Maziarz, K., Davis, A., Le, Q., Hinton, G., and Dean, J. (2017). Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv.
30. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity
31. Mixture-of-experts with expert choice routing
32. Liu, A., Feng, B., Xue, B., Wang, B., Wu, B., Lu, C., Zhao, C., Deng, C., Zhang, C., and Ruan, C. (2024). Deepseek-v3 technical report. arXiv.
33. Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., and Anadkat, S. (2023). Gpt-4 technical report. arXiv.
34. Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., and Liu, Z. (2024). Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv.10.18653/v1/2024.findings-acl.137 ↗
35. Feng, Z., Guo, D., Tang, D., Duan, N., Feng, X., Gong, M., Shou, L., Qin, B., Liu, T., and Jiang, D. (2020). Codebert: A pre-trained model for programming and natural languages. arXiv.10.18653/v1/2020.findings-emnlp.139 ↗
36. Zheng, Q., Xia, X., Zou, X., Dong, Y., Wang, S., Xue, Y., Shen, L., Wang, Z., Wang, A., and Li, Y. (2023, January 6–10). Codegeex: A pre-trained model for code generation with multilingual benchmarking on humaneval-x. Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Long Beach, CA, USA.10.1145/3580305.3599790 ↗
37. Retrieval-augmented generation for knowledge-intensive nlp tasks
38. Kaufmann, T., Weng, P., Bengs, V., and Hüllermeier, E. (2023). A survey of reinforcement learning from human feedback. arXiv.
39. Finardi, P., Avila, L., Castaldoni, R., Gengo, P., Larcher, C., Piau, M., Costa, P., and Caridá, V. (2024). The chronicles of rag: The retriever, the chunk and the generator. arXiv.
40. The probabilistic relevance framework: BM25 and beyond10.1561/1500000019 ↗
41. Lipani, A., Lupu, M., Hanbury, A., and Aizawa, A. (2015, January 27–30). Verboseness fission for bm25 document length normalization. Proceedings of the 2015 International Conference on the Theory of Information Retrieval, Northampton, MA, USA.10.1145/2808194.2809486 ↗
42. Direct preference optimization: Your language model is secretly a reward model
43. QLoRa: Efficient finetuning of quantized llms
44. Chain-of-thought prompting elicits reasoning in large language models
45. Geng, M., Wang, S., Dong, D., Wang, H., Li, G., Jin, Z., Mao, X., and Liao, X. (2024, January 14–20). Large language models are few-shot summarizers: Multi-intent comment generation via in-context learning. Proceedings of the 46th IEEE/ACM International Conference on Software Engineering, Lisbon, Portugal.10.1145/3597503.3608134 ↗
46. Zhong, X., Tang, J., and Yepes, A.J. (2019, January 20–25). Publaynet: Largest dataset ever for document layout analysis. Proceedings of the 2019 International Conference on Document Analysis and Recognition (ICDAR), Sydney, Australia.10.1109/ICDAR.2019.00166 ↗