Proposal for a Role-Based Multi-Agent LLM Architecture for Corporate Software Delivery
Resumo
Large language models (LLMs) have advanced from one-shot code generation to agents that iteratively interact with development environments. Their evaluation, however, remains detached from how software is delivered in companies: dominant benchmarks measure isolated, self-contained tasks, and most multi-agent frameworks operate in greenfield scenarios, disconnected from the repositories, review processes, staging environments and people that constitute a real delivery flow. This short paper proposes a role-based multiagent architecture, with Product, Architect, Engineer, Reviewer and QA agents, that covers the flow end-to-end from requirement refinement to staging validation. It uses the version-control platform itself as the communication and traceability medium, advances through staged validation gates, and keeps humans reachable at every step through a team manifest. Our main contribution is an agentic software development life cycle grounded in a survey of LLM-based agent approaches relevant to corporate delivery (multi-agent frameworks, benchmarks, requirements refinement and quality assurance), together with an evaluation protocol based on real issues from production repositories and centered on acceptance-criteria coverage.
Palavras-chave:
LLM Agents, Multi-Agent Systems, Software Engineering, Human-in-the-Loop, Acceptance Criteria, Software Delivery Automation
Referências
Adam Alami, Victor Jensen, and Neil Ernst. 2025. Accountability in Code Review: The Role of Intrinsic Drivers and the Impact of LLMs. ACM Trans. Softw. Eng. Methodol. 34, 8, Article 233 (Oct. 2025), 44 pages. DOI: 10.1145/3721127
Fredy Antonio Almeyda Alania, Alfredo Barrientos Padilla, and Ronald Gustavo Siancas Garay. 2025. Engineering Prompt-Orchestrated LLM Workflows for Automated Test Case Generation in Agile Environments. International Journal of Advanced Computer Science and Applications 16, 12 (2025). DOI: 10.14569/IJACSA.2025.0161272
Eranga Bandara, Ross Gore, Xueping Liang, Sachini Rajapakse, Isurunima Kularathne, Pramoda Karunarathna, Peter Foytik, Sachin Shetty, Ravi Mukkamala, Abdul Rahman, Amin Hass, Ng Wee Keong, Kasun De Zoysa, Aruna Withanage, and Nilaan Loganathan. 2025. Agentsway – Software Development Methodology for AI Agents-based Teams. arXiv:2510.23664 [cs.SE] [link]
Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, Nick Ryder, Mikhail Pavlov, Alethea Power, Lukasz Kaiser, Mohammad Bavarian, Clemens Winter, Philippe Tillet, Felipe Petroski Such, Dave Cummings, Matthias Plappert, Fotios Chantzis, Elizabeth Barnes, Ariel Herbert-Voss, William Hebgen Guss, Alex Nichol, Alex Paino, Nikolas Tezak, Jie Tang, Igor Babuschkin, Suchir Balaji, Shantanu Jain, William Saunders, Christopher Hesse, Andrew N. Carr, Jan Leike, Josh Achiam, Vedant Misra, Evan Morikawa, Alec Radford, Matthew Knight, Miles Brundage, Mira Murati, Katie Mayer, Peter Welinder, Bob McGrew, Dario Amodei, Sam McCandlish, Ilya Sutskever, and Wojciech Zaremba. 2021. Evaluating Large Language Models Trained on Code. arXiv:2107.03374 [cs.LG] [link]
Antoine Chevrot, Alexandre Vernotte, Jean-Rémy Falleri, Xavier Blanc, and Bruno Legeard. 2025. Are Autonomous Web Agents Good Testers? arXiv:2504.01495 [cs.SE] [link]
CrewAI, Inc. [n. d.]. CrewAI: Framework for Orchestrating Role-Playing, Autonomous AI Agents. [link].
Burak Gülmez. 2026. Code generation with large language models: a survey from neural program synthesis to autonomous software development. Applied Intelligence 56, 6 (2026), 200. DOI: 10.1007/s10489-026-07230-0
Tingxu Han, Yi Zhang, Wei Song, Chunrong Fang, Zhenyu Chen, Youcheng Sun, and Lijie Hu. 2026. SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering? arXiv:2603.15401 [cs.SE] [link]
Sirui Hong, Mingchen Zhuge, Jiaqi Chen, Xiawu Zheng, Yuheng Cheng, Ceyao Zhang, Jinlin Wang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and Jürgen Schmidhuber. 2024. MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework. arXiv:2308.00352 [cs.AI] [link]
Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan. 2024. SWE-bench: Can Language Models Resolve Real-World GitHub Issues? arXiv:2310.06770 [cs.CL] [link]
Jens Kohl, Otto Kruse, Youssef Mostafa, Andre Luckow, Karsten Schroer, Thomas Riedl, Ryan French, David Katz, Manuel P. Luitz, Tanrajbir Takher, Ken E. Friedl, and Céline Laurent-Winter. 2026. Automated structural testing of LLM-based agents: methods, framework, and case studies. arXiv:2601.18827 [cs.SE] [link]
Ravikanth Konda. 2025. Agentic AI for Software Development: Autonomous Agents in Requirements Engineering, Testing, and Deployment. International Journal of Emerging Research in Engineering and Technology (Nov. 2025), 139–148. DOI: 10.63282/3050-922X.AECTIC-118
Lang Chain, Inc. [n. d.]. LangGraph: Low-Level Orchestration Framework for Building Stateful Agents. [link].
Xinyi Li, Sai Wang, Siqi Zeng, Yu Wu, and Yi Yang. 2024. A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges. Vicinagearth 1, 1 (2024), 9. DOI: 10.1007/s44336-024-00009-2
Junwei Liu, Kaixin Wang, Yixuan Chen, Xin Peng, Zhenpeng Chen, Lingming Zhang, and Yiling Lou. 2026. Large Language Model-Based Agents for Software Engineering: A Survey. ACM Trans. Softw. Eng. Methodol. (March 2026). DOI: 10. 1145/3796507 Just Accepted.
Michele Merler, Rangeet Pan, Rahul Krishna, Tin Kam Ho, Raju Pavuluri, and Maja Vukovic. 2026. Usage, Effects and Requirements for AI Coding Assistants in the Enterprise: An Empirical Study. In Proceedings of the 3rd International Workshop on Large Language Models For Code (LLM4Code ’26). ACM, New York, NY, USA, 97–104. DOI: 10.1145/3786181.3788727
Nesreen Otoum and Nuha Elkhalili. 2026. Methods and Techniques of Agentic Software Engineering: A Systematic Literature Review. IEEE Access 14 (2026), 7443–7465.
Chanathip Pornprasit and Chakkrit Tantithamthavorn. 2024. Fine-tuning and prompt engineering for large language models-based code review automation. Information and Software Technology 175 (2024), 107523. DOI: 10.1016/j.infsof.2024.107523
Chen Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, Juyuan Xu, Dahai Li, Zhiyuan Liu, and Maosong Sun. 2024. ChatDev: Communicative Agents for Software Development. arXiv:2307.07924 [cs.SE] [link]
Giovanni Quattrocchi, Liliana Pasquale, Paola Spoletini, and Luciano Baresi. 2025. Can LLMs Generate User Stories and Assess Their Quality? arXiv:2507.15157 [cs.SE] [link]
Thanigaivel Rangasamy. 2026. Agentic AI-Driven Product Development Life Cycle. Journal of Computational Analysis & Applications 35, 1 (2026), 832.
Jessica Rawson and Sandeep Reddivari. 2025. A ChatGPT-powered Prompt Engineering Framework for Generating Software Acceptance Criteria. In Proceedings of the 2025 ACM Southeast Conference (Southeast Missouri State University, Cape Girardeau, MO, USA) (ACMSE 2025). Association for Computing Machinery, New York, NY, USA, 282–288. DOI: 10.1145/3696673.3723078
Wannita Takerngsaksiri, Jirat Pasuksmit, Patanamon Thongtanunam, Chakkrit Tantithamthavorn, Ruixiong Zhang, Fan Jiang, Jing Li, Evan Cook, Kun Chen, and Ming Wu. 2025. Human-In-the-Loop Software Development Agents. arXiv:2411.12924 [cs.SE] [link]
Fernando Vallecillos Ruiz. 2024. Agent-Driven Automatic Software Improvement. In Proceedings of the 28th International Conference on Evaluation and Assessment in Software Engineering (EASE 2024). ACM, New York, NY, USA, 470–475. DOI: 10.1145/3661167.3661171
Fanyu Wang, Chetan Arora, Yonghui Liu, Kaicheng Huang, Chakkrit Tantithamthavorn, Aldeida Aleti, Dishan Sambathkumar, and David Lo. 2025. Multi-Modal Requirements Data-based Acceptance Criteria Generation using LLMs. arXiv:2508.06888 [cs.SE] [link]
Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, Wayne Xin Zhao, Zhewei Wei, and Jirong Wen. 2024. A survey on large language model based autonomous agents. Frontiers of Computer Science 18, 6 (2024), 186345. DOI: 10.1007/s11704-024-40231-1
Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Hassan Awadallah, Ryen W White, Doug Burger, and Chi Wang. 2023. AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation. arXiv:2308.08155 [cs.AI] [link]
Frank F. Xu, Yufan Song, Boxuan Li, Yuxuan Tang, Kritanjali Jain, Mengxue Bao, Zora Z. Wang, Xuhui Zhou, Zhitong Guo, Murong Cao, Mingyang Yang, Hao Yang Lu, Amaad Martin, Zhe Su, Leander Maben, Raj Mehta, Wayne Chi, Lawrence Jang, Yiqing Xie, Shuyan Zhou, and Graham Neubig. 2025. The Agent-Company: Benchmarking LLM Agents on Consequential Real World Tasks. arXiv:2412.14161 [cs.CL] [link]
John Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press. 2024. SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering. arXiv:2405.15793 [cs.SE] [link]
Zheying Zhang, Maruf Rayhan, Tomas Herda, Manuel Goisauf, and Pekka Abrahamsson. 2024. LLM-Based Agents for Automating the Enhancement of User Story Quality: An Early Report. 117–126 pages. DOI: 10.1007/978-3-031-61154-4_8
Fredy Antonio Almeyda Alania, Alfredo Barrientos Padilla, and Ronald Gustavo Siancas Garay. 2025. Engineering Prompt-Orchestrated LLM Workflows for Automated Test Case Generation in Agile Environments. International Journal of Advanced Computer Science and Applications 16, 12 (2025). DOI: 10.14569/IJACSA.2025.0161272
Eranga Bandara, Ross Gore, Xueping Liang, Sachini Rajapakse, Isurunima Kularathne, Pramoda Karunarathna, Peter Foytik, Sachin Shetty, Ravi Mukkamala, Abdul Rahman, Amin Hass, Ng Wee Keong, Kasun De Zoysa, Aruna Withanage, and Nilaan Loganathan. 2025. Agentsway – Software Development Methodology for AI Agents-based Teams. arXiv:2510.23664 [cs.SE] [link]
Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, Nick Ryder, Mikhail Pavlov, Alethea Power, Lukasz Kaiser, Mohammad Bavarian, Clemens Winter, Philippe Tillet, Felipe Petroski Such, Dave Cummings, Matthias Plappert, Fotios Chantzis, Elizabeth Barnes, Ariel Herbert-Voss, William Hebgen Guss, Alex Nichol, Alex Paino, Nikolas Tezak, Jie Tang, Igor Babuschkin, Suchir Balaji, Shantanu Jain, William Saunders, Christopher Hesse, Andrew N. Carr, Jan Leike, Josh Achiam, Vedant Misra, Evan Morikawa, Alec Radford, Matthew Knight, Miles Brundage, Mira Murati, Katie Mayer, Peter Welinder, Bob McGrew, Dario Amodei, Sam McCandlish, Ilya Sutskever, and Wojciech Zaremba. 2021. Evaluating Large Language Models Trained on Code. arXiv:2107.03374 [cs.LG] [link]
Antoine Chevrot, Alexandre Vernotte, Jean-Rémy Falleri, Xavier Blanc, and Bruno Legeard. 2025. Are Autonomous Web Agents Good Testers? arXiv:2504.01495 [cs.SE] [link]
CrewAI, Inc. [n. d.]. CrewAI: Framework for Orchestrating Role-Playing, Autonomous AI Agents. [link].
Burak Gülmez. 2026. Code generation with large language models: a survey from neural program synthesis to autonomous software development. Applied Intelligence 56, 6 (2026), 200. DOI: 10.1007/s10489-026-07230-0
Tingxu Han, Yi Zhang, Wei Song, Chunrong Fang, Zhenyu Chen, Youcheng Sun, and Lijie Hu. 2026. SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering? arXiv:2603.15401 [cs.SE] [link]
Sirui Hong, Mingchen Zhuge, Jiaqi Chen, Xiawu Zheng, Yuheng Cheng, Ceyao Zhang, Jinlin Wang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and Jürgen Schmidhuber. 2024. MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework. arXiv:2308.00352 [cs.AI] [link]
Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan. 2024. SWE-bench: Can Language Models Resolve Real-World GitHub Issues? arXiv:2310.06770 [cs.CL] [link]
Jens Kohl, Otto Kruse, Youssef Mostafa, Andre Luckow, Karsten Schroer, Thomas Riedl, Ryan French, David Katz, Manuel P. Luitz, Tanrajbir Takher, Ken E. Friedl, and Céline Laurent-Winter. 2026. Automated structural testing of LLM-based agents: methods, framework, and case studies. arXiv:2601.18827 [cs.SE] [link]
Ravikanth Konda. 2025. Agentic AI for Software Development: Autonomous Agents in Requirements Engineering, Testing, and Deployment. International Journal of Emerging Research in Engineering and Technology (Nov. 2025), 139–148. DOI: 10.63282/3050-922X.AECTIC-118
Lang Chain, Inc. [n. d.]. LangGraph: Low-Level Orchestration Framework for Building Stateful Agents. [link].
Xinyi Li, Sai Wang, Siqi Zeng, Yu Wu, and Yi Yang. 2024. A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges. Vicinagearth 1, 1 (2024), 9. DOI: 10.1007/s44336-024-00009-2
Junwei Liu, Kaixin Wang, Yixuan Chen, Xin Peng, Zhenpeng Chen, Lingming Zhang, and Yiling Lou. 2026. Large Language Model-Based Agents for Software Engineering: A Survey. ACM Trans. Softw. Eng. Methodol. (March 2026). DOI: 10. 1145/3796507 Just Accepted.
Michele Merler, Rangeet Pan, Rahul Krishna, Tin Kam Ho, Raju Pavuluri, and Maja Vukovic. 2026. Usage, Effects and Requirements for AI Coding Assistants in the Enterprise: An Empirical Study. In Proceedings of the 3rd International Workshop on Large Language Models For Code (LLM4Code ’26). ACM, New York, NY, USA, 97–104. DOI: 10.1145/3786181.3788727
Nesreen Otoum and Nuha Elkhalili. 2026. Methods and Techniques of Agentic Software Engineering: A Systematic Literature Review. IEEE Access 14 (2026), 7443–7465.
Chanathip Pornprasit and Chakkrit Tantithamthavorn. 2024. Fine-tuning and prompt engineering for large language models-based code review automation. Information and Software Technology 175 (2024), 107523. DOI: 10.1016/j.infsof.2024.107523
Chen Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, Juyuan Xu, Dahai Li, Zhiyuan Liu, and Maosong Sun. 2024. ChatDev: Communicative Agents for Software Development. arXiv:2307.07924 [cs.SE] [link]
Giovanni Quattrocchi, Liliana Pasquale, Paola Spoletini, and Luciano Baresi. 2025. Can LLMs Generate User Stories and Assess Their Quality? arXiv:2507.15157 [cs.SE] [link]
Thanigaivel Rangasamy. 2026. Agentic AI-Driven Product Development Life Cycle. Journal of Computational Analysis & Applications 35, 1 (2026), 832.
Jessica Rawson and Sandeep Reddivari. 2025. A ChatGPT-powered Prompt Engineering Framework for Generating Software Acceptance Criteria. In Proceedings of the 2025 ACM Southeast Conference (Southeast Missouri State University, Cape Girardeau, MO, USA) (ACMSE 2025). Association for Computing Machinery, New York, NY, USA, 282–288. DOI: 10.1145/3696673.3723078
Wannita Takerngsaksiri, Jirat Pasuksmit, Patanamon Thongtanunam, Chakkrit Tantithamthavorn, Ruixiong Zhang, Fan Jiang, Jing Li, Evan Cook, Kun Chen, and Ming Wu. 2025. Human-In-the-Loop Software Development Agents. arXiv:2411.12924 [cs.SE] [link]
Fernando Vallecillos Ruiz. 2024. Agent-Driven Automatic Software Improvement. In Proceedings of the 28th International Conference on Evaluation and Assessment in Software Engineering (EASE 2024). ACM, New York, NY, USA, 470–475. DOI: 10.1145/3661167.3661171
Fanyu Wang, Chetan Arora, Yonghui Liu, Kaicheng Huang, Chakkrit Tantithamthavorn, Aldeida Aleti, Dishan Sambathkumar, and David Lo. 2025. Multi-Modal Requirements Data-based Acceptance Criteria Generation using LLMs. arXiv:2508.06888 [cs.SE] [link]
Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, Wayne Xin Zhao, Zhewei Wei, and Jirong Wen. 2024. A survey on large language model based autonomous agents. Frontiers of Computer Science 18, 6 (2024), 186345. DOI: 10.1007/s11704-024-40231-1
Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Hassan Awadallah, Ryen W White, Doug Burger, and Chi Wang. 2023. AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation. arXiv:2308.08155 [cs.AI] [link]
Frank F. Xu, Yufan Song, Boxuan Li, Yuxuan Tang, Kritanjali Jain, Mengxue Bao, Zora Z. Wang, Xuhui Zhou, Zhitong Guo, Murong Cao, Mingyang Yang, Hao Yang Lu, Amaad Martin, Zhe Su, Leander Maben, Raj Mehta, Wayne Chi, Lawrence Jang, Yiqing Xie, Shuyan Zhou, and Graham Neubig. 2025. The Agent-Company: Benchmarking LLM Agents on Consequential Real World Tasks. arXiv:2412.14161 [cs.CL] [link]
John Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press. 2024. SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering. arXiv:2405.15793 [cs.SE] [link]
Zheying Zhang, Maruf Rayhan, Tomas Herda, Manuel Goisauf, and Pekka Abrahamsson. 2024. LLM-Based Agents for Automating the Enhancement of User Story Quality: An Early Report. 117–126 pages. DOI: 10.1007/978-3-031-61154-4_8
Publicado
11/09/2026
Como Citar
PELOSO, Alisson Luan de Lima; BEVILACQUA, Fernando.
Proposal for a Role-Based Multi-Agent LLM Architecture for Corporate Software Delivery. In: WORKSHOP DE VISUALIZAÇÃO, EVOLUÇÃO E MANUTENÇÃO DE SOFTWARE (VEM), 14. , 2026, São Paulo/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 194-198.
DOI: https://doi.org/10.5753/vem.2026.33013.
