AutoEnergyDesign: An LLM-Driven Agent for Automatic Energy System Design Optimization

📄 arXiv: 2610.35160v1 📥 PDF

作者: Amedeo Buonanno, Salvatore Fabozzi, Maria Valenti

分类: cs.AI, stat.ML

发布日期: 2026-10-26


💡 一句话要点

提出AutoEnergyDesign以优化建筑能源系统设计

🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 建筑能源系统 优化设计 大型语言模型 智能代理 可持续发展

📋 核心要点

  1. 建筑能源系统设计面临高维度和混合整数搜索的挑战,传统方法效率低下。
  2. AutoEnergyDesign框架通过LLM代理推理和学习,结合记忆组织和撤回机制,优化设计过程。
  3. 实验显示,该代理在多次模拟中实现了优于传统优化方法的设计效果,显著减少了评估次数。

📝 摘要(中文)

建筑能源系统设计是一个高维度的混合整数搜索问题,传统的黑箱优化器通常需要数百次评估。本文提出了AutoEnergyDesign框架,该框架利用大型语言模型(LLM)代理对先前的模拟结果进行推理,提出配置变更并从每个结果中学习,同时通过基于git的机制自动撤回不成功的变更。该代理结合了推理模型与明确的记忆组织(程序性、语义性、情节性和反思性),并具有受限的动作接口和环境驱动的保留/撤回信号。实验结果表明,该代理在多个基准测试中表现优异,显著减少了所需的评估次数。

🔬 方法详解

问题定义:本文旨在解决建筑能源系统设计中的高维度混合整数搜索问题,现有方法通常需要大量的评估才能找到最优解,效率低下。

核心思路:提出的AutoEnergyDesign框架利用大型语言模型(LLM)代理,通过对历史模拟结果的推理和学习,提出新的设计配置,并在不成功时自动撤回变更,从而提高设计效率。

技术框架:该框架包括多个模块:LLM代理负责推理和学习,记忆组织模块存储不同类型的信息(程序性、语义性、情节性和反思性),以及一个受限的动作接口和环境驱动的信号机制。

关键创新:最重要的创新在于将LLM与明确的记忆组织相结合,使得代理能够在设计过程中进行有效的推理和学习,同时通过git机制实现动态撤回不成功的设计变更。

关键设计:在设计中,代理的决策过程被记录为可审计的痕迹,确保每一步的透明性和可追溯性。代理的运行依赖于Claude Haiku、Sonnet和Opus等模型,经过多次模拟优化设计。实验中还涉及到25年净现值(NPC)的计算,包括资本和运营成本。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果表明,AutoEnergyDesign代理在10次运行中均能达到约3.53 MEUR的NPC,优于最佳的TPE结果1.20%和最佳进化策略结果0.23%。在仅需18到27.5次模拟的情况下,代理能够接近最优设计,而传统方法则需192次评估才能达到类似效果。

🎯 应用场景

该研究的潜在应用领域包括建筑设计、能源管理和智能城市规划等。通过优化建筑能源系统设计,能够有效降低能耗和运营成本,提升可持续性,具有重要的实际价值和社会影响。未来,该框架可扩展至其他能源系统的设计与优化,推动智能能源解决方案的发展。

📄 摘要(原文)

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.