Metraipolis › archive › dc_01fe013ec843

LLMDE: A Large Language Model-Driven Differential Evolution Algorithm for Portfolio Optimization — arXiv:2609.16846

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.16846
License (as archived): CC0-1.0
Archived: 2026-10-15T21:44:18.669Z
SHA-256 of the archived text: 0cab22175a02a3a442442b8573b67055953beb1bd40e1e5a15f9a7c3bda3148b
Stable URL of this page: https://metraipolis.com/documento/dc_01fe013ec843

How to cite

LLMDE: A Large Language Model-Driven Differential Evolution Algorithm for Portfolio Optimization — arXiv:2609.16846 — arXiv (en), https://arxiv.org/abs/2609.16846 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_01fe013ec843 (Metraipolis archive dc_01fe013ec843, sha256 0cab22175a02a3a442442b8573b67055953beb1bd40e1e5a15f9a7c3bda3148b)

BibTeX

@misc{dc01fe013ec843,
  title = {LLMDE: A Large Language Model-Driven Differential Evolution Algorithm for Portfolio Optimization — arXiv:2609.16846},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16846},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_01fe013ec843; sha256 0cab22175a02a3a442442b8573b67055953beb1bd40e1e5a15f9a7c3bda3148b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16846. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This study proposes a Large Language Model-Driven Differential Evolution (LLMDE) algorithm to reduce the reliance on handcrafted hyperparameter design. The proposed algorithm leverages a prompt engineering strategy, allowing large language models (LLMs) to dynamically select mutation strategies and configure control parameters guided by optimization feedback, thus enhancing the performance of the DE algorithm. We evaluate the performance of LLMDE on the CEC2022 benchmark suite, comparing it with standard DE and representative metaheuristics. Furthermore, we employ factor analysis and K-means clustering for stock selection, and then apply LLMDE to solve the Conditional Value at Risk (CVaR) portfolio optimization problem using the selected stocks, subject to budget and minimum expected return constraints. Experimental results demonstrate that LLMDE achieves competitive performance on the benchmark suite while continuously generating high-quality solutions for complex constrained optimization tasks. These outcomes successfully demonstrate the viability of embedding LLMs within metaheuristics, paving a promising path toward the design of advanced LLM-assisted optimization techniques.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.NE).
Categorie arXiv: Neural and Evolutionary Computing (cs.NE).
Pagina del lavoro: https://arxiv.org/abs/2609.16846 — 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 2026-10-15T21:31:16.107Z dalla pagina https://arxiv.org/catchup/cs.NE/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).