Muhammad Waseem

From Specification to Service: Accelerating API-First Development Using Multi-Agent Systems

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

Large Language Models for Code Generation: The Practitioners Perspective

Large Language Models (LLMs) have emerged as coding assistants, capable of generating source code from natural language prompts. With the increasing adoption of LLMs in software development, academic research and industry based projects are developing various tools, benchmarks, and metrics to evaluate the effectiveness of LLM-generated code. However, there is a lack of solutions evaluated through empirically grounded methods that incorporate practitioners perspectives to assess functionality, syntax, and accuracy in real world applications. To address this gap, we propose and develop a multi-model unified platform to generate and execute code based on natural language prompts. We conducted a survey with 60 software practitioners from 11 countries across four continents working in diverse professional roles and domains to evaluate the usability, performance, strengths, and limitations of each model. The results present practitioners feedback and insights into the use of LLMs in software development, including their strengths and weaknesses, key aspects overlooked by benchmarks and metrics, and a broader understanding of their practical applicability. These findings can help researchers and practitioners make informed decisions for systematically selecting and using LLMs in software development projects. Future research will focus on integrating more diverse models into the proposed system, incorporating additional case studies, and conducting developer interviews for deeper empirical insights into LLM-driven software development.

VAPU: System for Autonomous Legacy Code Modernization

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.

Distributed Approach to Haskell Based Applications Refactoring with LLMs Based Multi-Agent Systems

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.

Assessing Small Language Models for Code Generation: An Empirical Study with Benchmarks

The recent advancements of Small Language Models (SLMs) have opened new possibilities for efficient code generation. SLMs offer lightweight and cost-effective alternatives to Large Language Models (LLMs), making them attractive for use in resource-constrained environments. However, empirical understanding of SLMs, particularly their capabilities, limitations, and performance trade-offs in code generation remains limited. This study presents a comprehensive empirical evaluation of 20 open-source SLMs ranging from 0.4B to 10B parameters on five diverse code-related benchmarks (HumanEval, MBPP, Mercury, HumanEvalPack, and CodeXGLUE). The models are assessed along three dimensions: i) functional correctness of generated code, ii) computational efficiency and iii) performance across multiple programming languages. The findings of this study reveal that several compact SLMs achieve competitive results while maintaining a balance between performance and efficiency, making them viable for deployment in resource-constrained environments. However, achieving further improvements in accuracy requires switching to larger models. These models generally outperform their smaller counterparts, but they require much more computational power. We observe that for 10% performance improvements, models can require nearly a 4x increase in VRAM consumption, highlighting a trade-off between effectiveness and scalability. Besides, the multilingual performance analysis reveals that SLMs tend to perform better in languages such as Python, Java, and PHP, while exhibiting relatively weaker performance in Go, C++, and Ruby. However, statistical analysis suggests these differences are not significant, indicating a generalizability of SLMs across programming languages. Based on the findings, this work provides insights into the design and selection of SLMs for real-world code generation tasks.

Vibe Coding in Practice: Flow, Technical Debt, and Guidelines for Sustainable Use

Vibe Coding (VC) is a form of software development assisted by generative AI, in which developers describe the intended functionality or logic via natural language prompts, and the AI system generates the corresponding source code. VC can be leveraged for rapid prototyping or developing the Minimum Viable Products (MVPs); however, it may introduce several risks throughout the software development life cycle. Based on our experience from several internally developed MVPs and a review of recent industry reports, this article analyzes the flow-debt tradeoffs associated with VC. The flow-debt trade-off arises when the seamless code generation occurs, leading to the accumulation of technical debt through architectural inconsistencies, security vulnerabilities, and increased maintenance overhead. These issues originate from process-level weaknesses, biases in model training data, a lack of explicit design rationale, and a tendency to prioritize quick code generation over human-driven iterative development. Based on our experiences, we identify and explain how current model, platform, and hardware limitations contribute to these issues, and propose countermeasures to address them, informing research and practice towards more sustainable VC approaches.

A Multi-agent LLM System for Automated Requirements Analysis: A Study on User Story Generation and Prioritization

Generative AI Adoption in an Energy Company: Exploring Challenges and Use Cases

Vibe Coding in Software Development: A Multivocal Literature Review

Vibe coding is a software development practice in which developers state intent in natural language and large language models generate code. It is often framed as one-shot prompting, but the evidence describes an intent-driven, iterative workflow whose outcomes depend on how generated code is evaluated and governed. Knowledge of how vibe coding is defined, practiced, and governed is scattered across academic and practitioner sources, and, to our knowledge, existing reviews have not yet integrated both evidence streams. We conducted a multivocal literature review of peer-reviewed and grey literature following established guidelines. Searches spanned 2022 to October 2025. After screening, credibility assessment, and snowballing, 47 sources were retained (28 peer-reviewed and 19 grey) and analyzed through descriptive mapping and thematic synthesis across eight research questions. Vibe coding is consistently described as an iterative generation-evaluation-revision loop rather than a one-shot activity, and developer work shifts from writing code towards specification, supervision, and validation. Short-term productivity and time-to-prototype gains are reported in 21 of 47 sources (45%), while evidence on maintainability, long-term quality, and safeguard effectiveness remains limited. Evidence is strongest for prototyping and user-interface work and weakest for production, data-intensive, and safety-critical use, and tool visibility does not imply effectiveness. This is one of the first reviews to integrate peer-reviewed and grey literature on vibe coding under a single documented protocol. Future work should evaluate safeguard effectiveness, study session-level dynamics and long-term maintainability, and test vibe coding in production, data-intensive, and safety-critical settings.

Context Before Code: An Experience Report on Vibe Coding in Practice

Code-generating tools are increasingly used in software development, yet experience reports on conversational"vibe coding"under production constraints remain limited. This paper presents an experience report from a small full-stack team that applied contextual prompting and explicit architectural constraints to build (i) a multi-project agent learning platform designed for sustained, production-oriented use and (ii) an academic retrieval-augmented generation system. The agent platform supports multiple isolated projects, each with structured memory and background processing, thereby enforcing project-level isolation. The RAG system provides citation-grounded answers, role-based access control, and evaluation tracking. Across both systems, vibe coding accelerated scaffolding and integration. However, the generated code often under-specified isolation rules and infrastructure constraints when these were not explicitly defined. Consequently, aspects such as multi-tenancy, access control, memory policies, and asynchronous processing required deliberate architectural design and verification. We observe a shift in engineering effort from boilerplate implementation toward constraint specification and enforcement auditing. We also identify recurring architectural"non-delegation zones"where conversational code generation remains insufficient for production reliability.

Identifying and Prioritizing Generative AI Use Cases in an Organization: An Industrial Case Study

Organisations are examining how generative AI can support their operational work and decision-making processes. This study investigates how employees in a energy company understand AI adoption and identify areas where AI and LLMs-based agentic workflows could assist daily activities. Data was collected in four weeks through sixteen semi-structured interviews across nine departments, supported by internal documents and researcher observations. The analysis identified areas where employees positioned AI as useful, including reporting work, forecasting, data handling, maintenance-related tasks, and anomaly detection. Participants also described how GenAI and LLM-based tools could be introduced through incremental steps that align with existing workflows. The study provides an overview view of AI adoption in the energy sector and offers a structured basis for identifying entry points for practical implementation and comparative research across industries.

Early Results of an AI Multiagent System for Requirements Elicitation and Analysis