Review
Open access
Jul 2026
Multi-Agent LLM Pipeline for Code Writing: An Experimental Study of Writer-Reviewer Architecture
A multi-agent pipeline-based approach for solving competitive programming problems via Large Language Models (LLMs) is developed and the Writer-Reviewer pipeline where the Writer Agent produces Python solutions and the Reviewer Agent gives static natural language feedback is analyzed.
Temel Kaan Ekiz, M. Z. Konyar
· ADBA Computer Science · 0 citations