Co4ICF: Co-evolving Physics-Informed Surrogate and RL-based Pulse Optimizer for Inertial Confinement Fusion
2026-07-11 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors address a problem where AI models used to optimize fusion experiments make mistakes when exploring unfamiliar inputs. They developed Co4ICF, a system where the AI optimizer and its supporting model improve together by learning from each other's results. This approach helps the model make better predictions during optimization, leading to much higher fusion yields in tests. Their method performed well even when tested in a more complex setting without extra training. They also provide a large dataset to help others test similar methods.
Inertial Confinement Fusionsurrogate modelout-of-distributionpolicy optimizationPPO1D MULTI2D MULTIco-evolutionlaser pulse designsimulation dataset
Authors
Jiatong Zhao, Tengyue Zhang, Yuhan Wang, Fuyuan Wu, Junchi Yan
Abstract
Offline-trained surrogates for Inertial Confinement Fusion (ICF) suffer a well-known failure mode that iterative optimizers drive inputs into out-of-distribution (OOD) regions where predictions become unreliable. Here we present Co4ICF, a co-evolving framework that couples a physics-informed surrogate with a PPO-based pulse optimizer. The surrogate is iteratively fine-tuned on policy-induced trajectories, correcting extrapolation errors as the optimizer shifts the input distribution; the optimizer queries this evolving surrogate as a fast environment. In the 1D MULTI environment, Co4ICF achieves 146.1% normalized yield based on current laser design baseline; as a post-hoc cross-fidelity check, the optimized pulse further attains 246.9% normalized yield when directly evaluated in 2D-MULTI without any 2D training or fine-tuning. Budget-matched ablations support that the gains are not explained solely by additional simulation data and are consistent with the co-evolving mechanism playing a key role. We release a large-scale MULTI-IFE simulation dataset to support future benchmarking.