Metraipolis › archive › dc_ff39d7b54874

Building LLM Agent Systems the Deep Learning Way: From Modular Design to Architecture Search — arXiv:2610.04961

Source
arXiv
Original
https://arxiv.org/abs/2610.04961
License (as archived)
CC0-1.0
Archived
2026-10-06T05:28:11.181Z
SHA-256 of the archived text
fa3463a6a65246ef5549cd2bbc16ddb8cf2b59246030d0b8dbf199f360213f9f
Stable URL of this page
https://metraipolis.com/documento/dc_ff39d7b54874

How to cite

Building LLM Agent Systems the Deep Learning Way: From Modular Design to Architecture Search — arXiv:2610.04961 — arXiv, https://arxiv.org/abs/2610.04961 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff39d7b54874 (Metraipolis archive dc_ff39d7b54874, sha256 fa3463a6a65246ef5549cd2bbc16ddb8cf2b59246030d0b8dbf199f360213f9f)
BibTeX
@misc{dcff39d7b54874,
  title = {Building LLM Agent Systems the Deep Learning Way: From Modular Design to Architecture Search — arXiv:2610.04961},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04961},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff39d7b54874; sha256 fa3463a6a65246ef5549cd2bbc16ddb8cf2b59246030d0b8dbf199f360213f9f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04961. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) have revolutionized AI research and enabled exciting agent systems. To build a complex LLM agent system, most existing research relies on insights from other domains or heuristics to manually build the agent system. However, this approach often requires heavy hand-engineering and fails to fully optimize for the downstream task of interest. Inspired by the tremendous success of deep learning, we propose to construct LLM agent systems in a modular manner, similar to building a deep neural network. Our key insight is to make analogies between LLM building blocks, such as retrievals, memories, and prompting strategies, and the successful deep learning modules, such as MLPs, attention, and recurrent modules. We further design forward inference and feedback mechanisms for LLMs, where prompts in LLMs are considered as the weights in deep models, and the prompt optimization from feedback is analogous to the back-propagation algorithm. We additionally leverage a search algorithm to search for the best configuration of LLM agent systems, similar to the neural architecture search (NAS) in deep learning research. Comprehensive experimental results demonstrate that the proposed deep learning recipe for LLM agent systems is highly effective, in particular: (1) Organizing LLM modules into deep-learning-style architectures yields noticeable performance gain; (2) Automatic prompt optimization, equivalent to backpropagation, is efficient in incorporating feedback from the task of interest and achieves at least 5% performance improvement; (3) NAS equivalent algorithm works well for further optimizing the LLM agent system architecture with 11% performance gain compared with randomly designed architectures. Overall, our research demonstrates the exciting opportunity of transferring the success of deep learning to building LLM agent systems.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.04961 — 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 2026-10-06T05:24:20.288Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).