Metraipolis › archive › dc_dae85706ab78
AutoEnergyDesign: An LLM-Driven Agent for Automatic Energy System Design Optimization — arXiv:2610.35160
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.35160
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:58:28.591Z
- SHA-256 of the archived text
13720d38e3d35dfd162c115eed2e134993e28135937792ac9fd06a3a0a94bdd3- Stable URL of this page
https://metraipolis.com/documento/dc_dae85706ab78
How to cite
AutoEnergyDesign: An LLM-Driven Agent for Automatic Energy System Design Optimization — arXiv:2610.35160 — arXiv (en), https://arxiv.org/abs/2610.35160 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dae85706ab78 (Metraipolis archive dc_dae85706ab78, sha256 13720d38e3d35dfd162c115eed2e134993e28135937792ac9fd06a3a0a94bdd3)
BibTeX
@misc{dcdae85706ab78,
title = {AutoEnergyDesign: An LLM-Driven Agent for Automatic Energy System Design Optimization — arXiv:2610.35160},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.35160},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dae85706ab78; sha256 13720d38e3d35dfd162c115eed2e134993e28135937792ac9fd06a3a0a94bdd3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.35160. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Designing building energy systems is a high-dimensional, mixed-integer search problem: when each design is evaluated by a year-long simulation, black-box optimizers typically need hundreds of evaluations. This paper presents AutoEnergyDesign, a framework in which a Large Language Model (LLM) agent reasons over previous simulation results, proposes configuration changes and learns in context from each outcome, while a git-based mechanism automatically reverts unsuccessful changes. The agent couples a reasoning model with an explicit memory organisation (procedural, semantic, episodic and reflective), a constrained action interface and an environment-grounded keep/revert signal. The simulator covers eight technologies (photovoltaics, micro-wind, combined heat and power, solar thermal, gas boilers, batteries, heat pumps and inverters) and computes the 25-year Net Present Cost (NPC), including capital and operating costs and salvage value. On a case study with measured building load profiles, the agent, run with Claude Haiku 5.5, Sonnet 5.5 and Opus 5.5 (ten runs of 50 simulations each), is compared with random search, Tree-structured Parzen Estimator (TPE) Bayesian optimization and a $(1+1)$ evolution strategy sharing the agent's acceptance rule (300 evaluations, ten seeds). With all three models the agent reaches an NPC of about 3.53 MEUR, 1.20% below the best TPE result and 0.23% below the best evolution-strategy result. It comes within 1% of this design after a median of 18 (Opus) to 27.5 (Haiku) simulations, whereas among the baselines only the evolution strategy does so, in half of its seeds and after a median of 192 evaluations. Opus reaches the best design in all ten runs, Sonnet in six (two runs never come within 1%), and Haiku comes within 1% in every run but reaches it exactly only once. Every decision is recorded in an auditable trace. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2610.35160 — 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 2026-10-27T07:55:30.738Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).