SHRAV: State-Hypothesis-Reason-Action-Verify Framework for Physical Modeling and Inverse Design

Ziheng Guo; Yang Bu

cs.AISep 23, 2026

SHRAV: State-Hypothesis-Reason-Action-Verify Framework for Physical Modeling and Inverse Design

Authors: Ziheng Guo, Yang Bu

Organizations: ZhangJiang Laboratory

Abstract

Physical modeling and inverse design require computation that can continue from reusable state. We introduce SHRAV, an architecture-independent computational framework organized around State, Hypothesis, Reason, Action, and Verify. Its central mechanism is a state-continuation core with declared reuse boundaries and explicit roles for learned evolution and numerical quantities. Forward configurations evolve predictive state and read out physical responses; inverse-design configurations additionally generate target-directed modifications and consume evaluator feedback. Electromagnetic world-model studies are mapped to forward configurations, with selected readout and reuse diagnostics reported here. Computational lithography demonstrates an inverse-design configuration: four fixed-weight design updates improve thresholded aerial-image intersection-over-union from 0.5313 to 0.8153 under independent scalar-pupil replay, with a maximum absolute IoU difference of approximately 0.000824 between predictor estimates and independent replay.

Explore similar work

LithoDreamer: A Physics-Informed World Model for Multi-Stage Computational Lithography
Jun 25, 2026Yuqi Jiang, Yumeng Liu, Zimu Li +7Lithography Physics-Informed Learning
Zhejiang University, No. 38 Zheda Road, Xihu District, Hangzhou, Zhejiang Province, China.
Reinforcement learning for inverse structural design and rapid laser cutting of kirigami prototypes
Apr 16, 2026Milad Yazdani, Shahriar Shalileh, Dena ShahriariGenerative Inverse Design Metamaterials
Department of Electrical and Computer Engineering, The University of British Columbia, 5500-2332 Main Mall, Vancouver, BC, V6T 1Z4, Canada · International Collaboration on Repair Discoveries (ICORD), Blusson Spinal Cord Centre, 818 West 10th Avenue, Vancouver, BC, V5Z 1M9, Canada · School of Biomedical Engineering, Biomedical Research Centre, The University of British Columbia, Room 251, 2222 Health Sciences Mall, Vancouver, BC, V6T 1Z3, Canada +1
Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design
May 19, 2026Elias Berger, Muhammad Usama, Jan Mehlstäubl +2Computer-Aided Design Objects Engineering
Dresden University of Technology, Dresden, Germany · MAN Truck & Bus SE, Munich, Germany · German Research Center for Artificial Intelligence, Kaiserslautern, Germany +1

Jun 25, 2026, cs.AIJ/K move · Enter open · S save

LithoDreamer: A Physics-Informed World Model for Multi-Stage Computational Lithography

Yuqi Jiang, Yumeng Liu, Zimu Li, Jinyuan Deng+6

Zhejiang University, No. 38 Zheda Road, Xihu District, Hangzhou, Zhejiang Province, China.

Lithography Physics-Informed Learning Dream Porous Media Latent Space Alphaevolve

Open paper AskPDF arXiv

As semiconductor technology nodes scale, computational lithography is essential for ensuring yield and performance. However, lithography is a continuous physical process involving mask optimization, optical imaging, resist exposure, and development, which existing models fail to capture. To overcome this limitation, we present LithoDreamer, the first physics-informed World Model (WM) framework for computational lithography, which formulates the ``Layout-Mask-Resist Image-After Development Image (ADI)'' pipeline as a decision-driven multi-step evolution system. LithoDreamer captures feature changes between adjacent states to model stage-specific physics-informed latent spaces, in which it controls process intervention exploration and drives subsequent state transitions. To achieve interpretable intervention optimization without continuous supervision, we propose a contrastive variational optimization paradigm that contrasts the latent differences between intervention paths with variational evolution constraints, guiding the model to generate evolutions consistent with real lithography physics. Experiments show LithoDreamer achieves state-of-the-art performance in forward evolution and inverse planning. Our lithography dataset is publicly available at GitHub (https://github.com/7jiangyq/lithodreamer.git).

Abstract

Explore similar work

LithoDreamer: A Physics-Informed World Model for Multi-Stage Computational Lithography

Reinforcement learning for inverse structural design and rapid laser cutting of kirigami prototypes

Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design