Metraipolis › archive › dc_6eecdfbdfa06

AgentFactory: Towards Automated Agentic System Design and Optimization — arXiv:2609.01045

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.01045
License (as archived): CC0-1.0
Archived: 2026-10-17T06:32:16.935Z
SHA-256 of the archived text: 16d14116627844870885d66273282168452224d764cc522a16c2ca39f2acd02f
Stable URL of this page: https://metraipolis.com/documento/dc_6eecdfbdfa06

How to cite

AgentFactory: Towards Automated Agentic System Design and Optimization — arXiv:2609.01045 — arXiv (en), https://arxiv.org/abs/2609.01045 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6eecdfbdfa06 (Metraipolis archive dc_6eecdfbdfa06, sha256 16d14116627844870885d66273282168452224d764cc522a16c2ca39f2acd02f)

BibTeX

@misc{dc6eecdfbdfa06,
  title = {AgentFactory: Towards Automated Agentic System Design and Optimization — arXiv:2609.01045},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01045},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6eecdfbdfa06; sha256 16d14116627844870885d66273282168452224d764cc522a16c2ca39f2acd02f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01045. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) have demonstrated remarkable capabilities as powerful components in agentic systems, enabling sophisticated reasoning and complex task execution. However, current approaches to manually designing and optimizing agentic systems heavily rely on manual effort, limiting their adaptability and scalability. Recent work has explored the automated optimization of workflow designs. However, these approaches often overlook the crucial role of model capabilities and focus on single performance metrics, failing to address real-world deployment constraints. In this paper, we present AgentFactory, a framework that jointly optimizes both foundation models and workflow structures in agentic systems while considering multiple objectives including performance, cost, and efficiency. AgentFactory leverages advanced LLMs as optimizers to navigate the vast search space of possible configurations, employing a three-stage optimization pipeline to automatically discover effective combinations of fine-tuned models and optimized workflows. Through an iterative optimization process, our framework systematically explores and evaluates different agentic system designs, adapting to task-specific requirements while maintaining operational efficiency. We evaluate AgentFactory across eight benchmarks spanning five domains, including general reasoning, coding, mathematics, medicine, and finance. Our experiments demonstrate that AgentFactory consistently outperforms both manually designed methods and existing automated approaches, achieving an average improvement of 9.1% across all benchmarks, with particularly significant gains in domain-specific tasks (19.6% on MedQA and 18.7% on FinEval). These results establish AgentFactory as a promising approach for developing more capable and efficient agentic systems through automated optimization.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.01045 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T06:15:12.669Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).