Abstract
The rise of No-Code Development (NCD) has enabled citizen developers to build applications without traditional programming expertise. However, as these platforms scale to handle complex, interdependent tasks, their limitations become apparent.
Large Language Models (LLMs) offer a potential solution, yet single-agent systems often struggle to manage fullstack development reliably.
This study introduces MASON—a Multi-Agent System (MAS) for Open No-code development framework—that coordinates specialized LLM agents via a YAML-based workflow to automate NCD tasks. The system was evaluated
across four proprietary models—Claude 3.5 Sonnet, GPT- 4o Mini, Gemini 1.5 Flash, and DeepSeek-Chat—using HumanEval and MBPP benchmarks to assess accuracy, executiontime, and stability. MASON configurations showed improved
task reliability in simpler workflows but introduced latency on more complex tasks. Additional testing with small, locally hosted LLMs revealed significant limitations, emphasizing the need for architectural redesign or model fine-tuning
to support deployment in resource-constrained environments.
Large Language Models (LLMs) offer a potential solution, yet single-agent systems often struggle to manage fullstack development reliably.
This study introduces MASON—a Multi-Agent System (MAS) for Open No-code development framework—that coordinates specialized LLM agents via a YAML-based workflow to automate NCD tasks. The system was evaluated
across four proprietary models—Claude 3.5 Sonnet, GPT- 4o Mini, Gemini 1.5 Flash, and DeepSeek-Chat—using HumanEval and MBPP benchmarks to assess accuracy, executiontime, and stability. MASON configurations showed improved
task reliability in simpler workflows but introduced latency on more complex tasks. Additional testing with small, locally hosted LLMs revealed significant limitations, emphasizing the need for architectural redesign or model fine-tuning
to support deployment in resource-constrained environments.
| Original language | English |
|---|---|
| Publication status | Accepted/In press - 21 May 2025 |
| Event | Association for the Advancement of Artificial Intelligence Syposium on Human-AI Collaboration 2025: Exploring diversity of human cognitive abilities and varied AI models for hybrid intelligent systems - Heriot-Watt Campus, Dubai, United Arab Emirates Duration: 20 May 2025 → 22 May 2025 |
Conference
| Conference | Association for the Advancement of Artificial Intelligence Syposium on Human-AI Collaboration 2025 |
|---|---|
| Abbreviated title | AAAI SuS 2025 |
| Country/Territory | United Arab Emirates |
| City | Dubai |
| Period | 20/05/25 → 22/05/25 |