G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration
This addresses the problem of building accurate simulators for complex decision-making in domains like healthcare and logistics, but appears incremental as it combines existing LLM and calibration approaches.
The paper tackles the problem of constructing robust simulators for critical domains like healthcare and logistics, which often struggle with generalization or accuracy when using LLMs, by introducing G-Sim, a hybrid framework that combines LLM-driven structural design with gradient-free calibration techniques. The result is a method that produces reliable, causally-informed simulators capable of handling non-differentiable and stochastic systems, though no concrete performance numbers are provided.
Constructing robust simulators is essential for asking "what if?" questions and guiding policy in critical domains like healthcare and logistics. However, existing methods often struggle, either failing to generalize beyond historical data or, when using Large Language Models (LLMs), suffering from inaccuracies and poor empirical alignment. We introduce G-Sim, a hybrid framework that automates simulator construction by synergizing LLM-driven structural design with rigorous empirical calibration. G-Sim employs an LLM in an iterative loop to propose and refine a simulator's core components and causal relationships, guided by domain knowledge. This structure is then grounded in reality by estimating its parameters using flexible calibration techniques. Specifically, G-Sim can leverage methods that are both likelihood-free and gradient-free with respect to the simulator, such as gradient-free optimization for direct parameter estimation or simulation-based inference for obtaining a posterior distribution over parameters. This allows it to handle non-differentiable and stochastic simulators. By integrating domain priors with empirical evidence, G-Sim produces reliable, causally-informed simulators, mitigating data-inefficiency and enabling robust system-level interventions for complex decision-making.