灰箱仿真模型的智能校准：一种由大语言模型驱动的替代方法
Agentic Calibration of Grey-Box Simulation Models: An LLM-Driven Alternative
浏览论文内容
中文总结 AI 辅助
研究灰箱仿真模型校准问题，提出用大语言模型作优化器的智能校准方法，在肛门癌仿真模型上评估，结果表明该方法在减少模型评估次数上有优势，虽迭代推理时间增加，但可审计和解释，适用于仿真时间占主导的情况。
中文摘要 AI 辅助
灰箱仿真模型校准是一个约束优化问题，模型评估成本高、参数空间高维且搜索须遵循合理性约束。传统优化器如Nelder - Mead简单但采样效率低，现代贝叶斯优化方法评估次数少但处理约束复杂。本文引入智能校准方法，用大语言模型作优化器，将约束纳入系统提示。在肛门癌仿真模型上评估，无约束时智能方法误差低且评估次数少，有约束时与贝叶斯优化相当且优于传统方法，虽每次迭代推理时间增加，但评估次数大幅减少，且使搜索可审计和解释。
英文摘要
Calibration of grey-box simulation models is a constrained optimization problem in which model evaluations are expensive, the parameter space can be high-dimensional, and the search must respect plausibility constraints. Although the simulation code is fully available to the analyst, the joint effect of multiple parameters remains difficult to predict analytically. Classical optimizers such as Nelder--Mead (NM) are simple to deploy but sample-inefficient, particularly under constraints. Modern Bayesian Optimization methods achieve competitive solutions with far fewer evaluations but require non-trivial modeling machinery for constraint handling. We introduce an agentic calibration method in which a large language model acts as the optimizer, with constraints incorporated as a plain-language section of the system prompt. We evaluate the agentic method, NM, and Bayesian Optimization (BO) on an anal cancer simulation model under both unconstrained and clinically constrained calibration. Under unconstrained calibration, the agentic method achieves substantially lower best error than BO and NM, while requiring fewer model evaluations. Under constrained calibration, the agentic method reaches comparable error levels and both outperform NM. These results are obtained at the cost of increased inference time per iteration. Agentic calibration achieves competitive performance with substantially fewer model evaluations, and constraint handling is essentially free at the modeller-facing interface through simple textual specifications rather than additional modelling machinery. The main trade-off lies in increased per-iteration inference cost, making the approach particularly suitable when simulation time dominates. Beyond performance, the per-iteration rationale makes the search auditable and explainable, so its decisions can be scrutinised and justified to third parties.
发表机构
- Catalan Institute of Oncology-IDIBELL（加泰罗尼亚肿瘤研究所-IDIBELL）
- Autonomous University of Barcelona（巴塞罗那自治大学）
- Centro de Investigación Biomédica en Red de Epidemiología y Salud Pública（国家公共卫生与流行病学网络生物医学研究中心）
- Artificial Intelligence Research Institute, IIIA-CSIC（人工智能研究所，西班牙科学研究委员会-人工智能研究所）
机构由 AI 辅助整理，请以论文原文为准。
