Emerging Multi-AI Agent Framework for Autonomous Agentic AI Solution Optimization
Abstract
Agentic AI systems automate complex workflows but require extensive manual tuning. This paper presents a framework for autonomously optimizing Agentic AI solutions across industries, such as NLG-driven enterprise applications. It employs agents for Refinement, Execution, Evaluation, Modification, and Documentation, using iterative feedback loops powered by an LLM (Llama 3.2-3B). The system optimizes configurations without human input by autonomously generating and testing hypotheses, enhancing scalability and adaptability. Case studies demonstrate a significant boost in output quality, relevance, and actionability. Data, including original and evolved agent codes and outputs, are open-sourced.
Cite
Text
Yuksel and Sawaf. "Emerging Multi-AI Agent Framework for Autonomous Agentic AI Solution Optimization." ICLR 2025 Workshops: AgenticAI, 2025.Markdown
[Yuksel and Sawaf. "Emerging Multi-AI Agent Framework for Autonomous Agentic AI Solution Optimization." ICLR 2025 Workshops: AgenticAI, 2025.](https://mlanthology.org/iclrw/2025/yuksel2025iclrw-emerging/)BibTeX
@inproceedings{yuksel2025iclrw-emerging,
title = {{Emerging Multi-AI Agent Framework for Autonomous Agentic AI Solution Optimization}},
author = {Yuksel, Kamer Ali and Sawaf, Hassan},
booktitle = {ICLR 2025 Workshops: AgenticAI},
year = {2025},
url = {https://mlanthology.org/iclrw/2025/yuksel2025iclrw-emerging/}
}