A Comparative Analysis of Multi-Agent Frameworks for Automated Software Bug Resolution

This paper presented a comparative evaluation of five con-temporary multi-agent orchestration frameworks for automated software bug resolution. A Unified Multi-Agent Debugging Orchestration (UMADO) architecture was introduced to pro-vide framework-independent benchmarking while ensuring consistent task allocation across different execution environ-ments. The comparative analysis indicates that graph-oriented or-chestration frameworks provide superior workflow control and debugging consistency for complex software systems. Con-versely, lightweight frameworks reduce computational cost and simplify deployment, making them appropriate for educational environments and rapid prototyping. The proposed methodology contributes a reproducible benchmarking framework that enables objective comparison of collaborative AI systems designed for intelligent software maintenance.

[1]     A. Vaswani et al., “Attention is all you need,” in Advances in Neural Information Processing Systems, 2017. [2]     T. B. Brown et al., “Language models are few-shot learners,” Advances in Neural Information Processing Systems, vol. 33, pp. 1877–1901, 2020. [3]     H. Touvron et al., “Llama 2: Open foundation and fine-tuned chat models,” arXiv preprint arXiv:2307.09288, 2023. [4]     OpenAI, “Gpt-4 technical report,” arXiv preprint arXiv:2303.08774, 2023. [5]     J. Yang et al., “Swe-bench: Can language models resolve real-world github issues?” in International Conference on Learning Representa-tions, 2024. [6]     R. Just, D. Jalali, and M. D. Ernst, “Defects4j: A database of existing faults for java programs,” in Proceedings of ISSTA, 2014. [7]     M. Chen et al., “Evaluating large language models trained on code,” in arXiv preprint arXiv:2107.03374, 2021. [8]     R. S. Pressman and B. R. Maxim, Software Engineering: A Practi-tioner’s Approach, 9th ed. McGraw-Hill, 2019. [9]     I. Sommerville, Software Engineering, 10th ed.  Pearson, 2016. [10]    T. H. Cormen et al., Introduction to Algorithms, 4th ed. MIT Press, 2022.