Context: LLM-based multi-agent systems enable automation and decision support in software development, yet existing studies rely on benchmark datasets offering only binary pass-or-fail results, limiting insight into real-world applicability. Objective: This study empirically investigates the potential and limitations of LLM-based agents in autonomous software development tasks. Method: A two-phase approach was employed: developing a multi-agent system, CodePori, for automated code generation, and conducting participant-based evaluation to assess practical performance. Results: Participant feedback reveals key strengths, challenges, and areas for improvement in LLM-based multi-agent systems, highlighting aspects missed by standard code-generation benchmarks. Conclusions: While LLM-based multi-agent systems show potential for large-scale software development, successful integration requires addressing challenges such as memory limitations, hallucinations, and code smells, alongside a practitioner-centric perspective.
Z. Rasheed, Muhammad Waseem, Kai-Kristian Kemell et al.· 31 citations
Collaborative AI experimentation in industry-academia requires environments that support rapid trials while maintaining controlled access, organisational isolation, and traceable workflows. Although interest in AI sandboxes is increasing, practical guidance on designing and building governance-aware experimentation platforms remains limited. This work designs and operationalizes a governance-aware, multi-tenant AI sandbox that supports structured experimentation and produces reusable evaluation evidence across stakeholders. The sandbox was developed in an industry-academia ecosystem using iteratively validated requirements gathered from industrial partners. The solution adopts a layered reference architecture that separates a multi-tenant presentation layer from a backend control plane and isolates execution and data management concerns into dedicated layers. The sandbox supports governed onboarding, project-based collaboration, controlled access to AI services, and traceable experimentation through approval workflows and audit logging. By structuring experiment context and governance decisions as persistent records, the sandbox enables evaluation evidence to be reused and compared across projects and stakeholders. The development experience yields lessons learned and practical considerations that inform deployment and future evolution of governance-aware sandbox platforms.
Muhammad Waseem, M. Islam, Md Nasir Uddin Shuvo et al.· arXiv.org· 0 citations
Collaborative AI experimentation across industry and academia requires platforms that enable rapid prototyping while preserving controlled access, tenant separation, and transparent workflows. Despite growing interest in AI sandboxes, there is still limited practical guidance on how to design and implement platforms that integrate experimentation capabilities with governance requirements. This work presents the design and implementation of a governance-aware, multi-tenant AI sandbox for structured experimentation and the generation of reusable evaluation evidence across projects and stakeholder groups. The sandbox was developed within an industry-academia collaboration based on requirements that were iteratively refined with industrial partners. Its reference architecture separates the multi-tenant user interface from the backend control plane and places execution and data-management functions in dedicated layers. The platform supports governed user onboarding, project-centered collaboration, managed access to AI services, approval workflows, audit logging, and traceable experimentation. Experiment configurations, contextual information, and governance decisions are stored as persistent records, allowing evidence and outcomes to be compared and reused across projects. The development process provides practical lessons for deploying and extending governance-aware AI sandbox platforms in collaborative research and industrial environments.
Muhammad Waseem, M. Islam, Md Nasir Uddin Shuvo et al.· 0 citations
Large Language Models (LLMs) have enabled multi-agent systems to perform autonomous code generation for complex tasks. Despite the recent growth in research and industrial applications in this area, there is little work on synthesizing evidence from both academic and industrial sources to capture the current state of research on LLM-based multi-agent systems for code generation. To this end, we conducted a Multi-Vocal Literature Review (MLR), combining insights from both academia and industry, including peer-reviewed studies and grey literature. The aim of this study is to systematically synthesize and analyze existing knowledge on LLM-based multi-agent systems for code generation. Specifically, the review examines the motivations for their use, employed benchmarks and models, key challenges, proposed solutions, and potential directions for future research. We selected and reviewed 114 studies, and the key findings are: 1) the identified reasons for adopting multi-agent systems for code generation were classified into nine categories; 2) the models and evaluation benchmarks utilized across the studies were systematically analyzed to provide a structured overview of commonly adopted LLM configurations and assessment practices; 3) the reported challenges and corresponding solutions were synthesized into six main categories and 26 subcategories; and 4) future research directions were identified and organized into six main categories and 18 subcategories. The results of this MLR will assist researchers and practitioners in pursuing further studies and supporting the real-world adoption of multi-agent systems in industrial settings.
Z. Rasheed, Muhammad Waseem, Kai-Kristian Kemell et al.· arXiv.org· 2 citations
Recent advances in agentic frameworks have enabled AI agents to perform complex reasoning and decision-making. However, evidence comparing their reasoning performance, efficiency, and practical suitability remains limited. To address this gap, we empirically evaluate 22 widely used agentic frameworks across three reasoning benchmarks: BBH, GSM8K, and ARC. The frameworks were selected from 1,200 GitHub repositories collected between January 2023 and July 2025 and organized into a taxonomy based on architectural design. We evaluated them under a unified setting, measuring reasoning accuracy, execution time, computational cost, and cross-benchmark consistency. Our results show that 19 of the 22 frameworks completed all three benchmarks. Among these, 12 showed stable performance, with mean accuracy of 74.6-75.9%, execution time of 4-6 seconds per task, and cost of 0.14-0.18 cents per task. Poorer results were mainly caused by orchestration problems rather than reasoning limits. For example, Camel failed to complete BBH after 11 days because of uncontrolled context growth, while Upsonic consumed USD 1,434 in one day because repeated extraction failures triggered costly retries. AutoGen and Mastra also exhausted API quotas through iterative interactions that increased prompt length without improving results. We also found a sharp drop in mathematical reasoning. Mean accuracy on GSM8K was 44.35%, compared with 89.80% on BBH and 89.56% on ARC. Overall, this study provides the first large-scale empirical comparison of agentic frameworks for reasoning-intensive software engineering tasks and shows that framework selection should prioritize orchestration quality, especially memory control, failure handling, and cost management.
Z. Rasheed, Malik Abdul Sami, Muhammad Waseem et al.· arXiv.org· 1 citation
Large language models are redefining software engineering by implementing AI-powered techniques throughout the whole software development process, including requirement gathering, software architecture, code generation, testing, and deployment. However, it is still difficult to develop a cohesive platform that consistently produces the best outcomes across all stages. The objective of this study is to develop a unified platform that utilizes multiple artificial intelligence agents to automate the process of transforming user requirements into well-organized deliverables. These deliverables include user stories, prioritization, and UML sequence diagrams, along with the modular approach to APIs, unit tests, and end-to-end tests. Additionally, the platform will organize tasks, perform security and compliance, and suggest design patterns and improvements for non-functional requirements. We allow users to control and manage each phase according to their preferences. In addition, the platform provides security and compliance checks following European standards and proposes design optimizations. We use multiple models, such as GPT-3.5, GPT-4, and Llama3 to enable to generation of modular code as per user choice. The research also highlights the limitations and future research discussions to overall improve the software development life cycle. The source code for our uniform platform is hosted on GitHub, enabling additional experimentation and supporting both research and practical uses. \end
Malik Abdul Sami, Muhammad Waseem, Z. Rasheed et al.· arXiv.org· 14 citations· ⚡1
Systematic literature review (SLR) is foundational to evidence-based research, enabling scholars to identify, classify, and synthesize existing studies to address specific research questions. Conducting an SLR is, however, largely a manual process. In recent years, researchers have made significant progress in automating portions of the SLR pipeline to reduce the effort and time required for high-quality reviews; nevertheless, there remains a lack of AI-agent-based systems that automate the entire SLR workflow. To this end, we introduce a novel multi-AI-agent system designed to fully automate SLRs. Leveraging large language models (LLMs), our system streamlines the review process to enhance efficiency and accuracy. Through a user-friendly interface, researchers specify a topic; the system then generates a search string to retrieve relevant academic papers. Next, an inclusion/exclusion filtering step is applied to titles relevant to the research area. The system subsequently summarizes paper abstracts and retains only those directly related to the field of study. In the final phase, it conducts a thorough analysis of the selected papers with respect to predefined research questions. This paper presents the system, describes its operational framework, and demonstrates how it substantially reduces the time and effort traditionally required for SLRs while maintaining comprehensiveness and precision. The code for this project is available at: https://github.com/GPT-Laboratory/SLR-automation .
Malik Abdul Sami, Z. Rasheed, Kai-Kristian Kemell et al.· arXiv.org· 43 citations· ⚡2
This paper presents a system that uses Large Language Models (LLMs)-based agents to automate the API-first development of RESTful microservices. This system helps to create an OpenAPI specification, generate server code from it, and refine the code through a feedback loop that analyzes execution logs and error messages. The integration of log analysis enables the LLM to detect and address issues efficiently, reducing the number of iterations required to produce functional and robust services. This study's main goal is to advance API-first development automation for RESTful web services and test the capability of LLM-based multi-agent systems in supporting the API-first development approach. To test the proposed system's potential, we utilized the PRAB benchmark. The results indicate that if we keep the OpenAPI specification small and focused, LLMs are capable of generating complete functional code with business logic that aligns to the specification. The code for the system is publicly available at https://github.com/sirbh/code-gen
Saurabh Chauhan, Z. Rasheed, Malik Abdul Sami et al.· arXiv.org· 1 citation
In this study, we present a solution for the modernization of legacy applications, an area of code generation where LLM-based multi-agent systems are proving essential for complex multi-phased tasks. Legacy applications often contain deprecated components that create compatibility, security, and reliability risks, but high resource costs make companies hesitate to update. We take a step forward to integrate an LLM-based multi-agent system as part of a legacy web application update to provide a cost-effective solution to update legacy applications autonomously. We propose a multi-agent system named a Verifying Agent Pipeline Updater (VAPU), which is designed to update code files in phases while simulating different roles in a software development team. In our previous study, we evaluated the system for legacy version updates by using six legacy web application view files by resulting errors and accomplished requirements. This study extends the previous evaluation of a multi-agent pipeline system by extending the evaluation of VAPU from a single LLM to five LLMs and using the temperature parameter in both 0 to 1 settings. Additionally, we tested the system with 20 open-source Python GitHub projects. The results of the evaluation were compared to Zero-Shot Learning (ZSL) and One-Shot Learning (OSL) prompts. The extended evaluation of VAPU showed that particularly in a low-temperature VAPU can get similar level of error count compared to the ZSL/OSL prompts but with a higher level of fulfilled requirements, depending on the LLM. VAPU showed up to 22.5% increase in the succeeding Python file update requirements compared to ZSL/OSL prompts. The study indicates that an LLM-based multi-agent system is a capable solution to update components of a legacy application autonomously.
Valtteri Ala-Salmi, Z. Rasheed, Malik Abdul Sami et al.· arXiv.org· 3 citations
We present a large language models (LLMs) based multi-agent system to automate the refactoring of Haskell codebases. The multi-agent system consists of specialized agents performing tasks such as context analysis, refactoring, validation, and testing. Refactoring improvements are using metrics such as cyclomatic complexity, run-time, and memory allocation. Experimental evaluations conducted on Haskell codebases demonstrate improvements in code quality. Cyclomatic complexity was reduced by 13.64% and 47.06% in the respective codebases. Memory allocation improved by 4.17% and 41.73%, while runtime efficiency increased by up to 50%. These metrics highlight the systems ability to optimize Haskells functional paradigms while maintaining correctness and scalability. Results show reductions in complexity and performance enhancements across codebases. The integration of LLMs based multi-agent system enables precise task execution and inter-agent collaboration, addressing the challenges of refactoring in functional programming. This approach aims to address the challenges of refactoring functional programming languages through distributed and modular systems.
Shahbaz Siddeeq, Z. Rasheed, Malik Abdul Sami et al.· arXiv.org· 1 citation
