AroundConnect

2024

A Multi-AI Agent System for Autonomous Optimization of Agentic AI Solutions via Iterative Refinement and LLM-Driven Feedback Loops

Yuksel, Kamer Ali, Sawaf, Hassan

Understand

Agentic AI systems use specialized agents to handle tasks within complex workflows, enabling automation and efficiency.

  • However, optimizing these systems often requires labor-intensive, manual adjustments to refine roles, tasks, and interactions.
  • This paper introduces a framework for autonomously optimizing Agentic AI solutions across industries, such as NLP-driven enterprise applications.
  • The system employs agents for Refinement, Execution, Evaluation, Modification, and Documentation, leveraging iterative feedback loops powered by an LLM (Llama 3.2-3B).

Built on

  • Professional agents: Evolving large language models

    Sarah Johnson and Ming Liu. 2023 · 2023

    Earlier work this paper cites.

  • Large model agents: State-of-the-art cooperation

    Jordan Smith, Liam O’Connor, and Divya Patel. 2023 · 2023

    Earlier work this paper cites.

  • Automated design of agentic systems

    Original

    Shengran Hu, Cong Lu, and Jeff Clune. 2024 · 2024

    Earlier work this paper cites.

  • Mlagentbench: Evaluating language agents on machine learning experimentation

    Qian Huang, Jian Vora, Percy Liang, and Jure Leskovec. 2024 · 2024

    Earlier work this paper cites.

Similar

Then

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…