cs.AINov 3, 2026

A research world model of power engineering learns its dynamics and reveals what-ifs

Authors: Fanping Sui, Ying Zhang, Liwei Lin

Organizations: Department of Mechanical Engineering, University of California, Berkeley, Berkeley, CA, USA · School of Electrical and Computer Engineering, Oklahoma State University, Stillwater, OK, USA

Abstract

Decisions about the direction of research in power engineering determine which technologies mature and, through them, shape infrastructure that lasts decades, yet their consequences cannot be observed before they are taken, and existing forecasts of research fields extrapolate a single trajectory. Here we introduce research world models, which treat a research field as a dynamical system that can be acted upon, and establish one for power engineering from 1.1 million papers. A distilled language model reads each paper into role-typed concepts, two sophisticated, high-fidelity graph-temporal neural network cores learn how the resulting concept network evolves, and operators learned from natural experiments in the publication record estimate the effects of interventions. In temporally held-out tests, the model forecast years ahead which concepts would grow and which method-target pairs would be joined for the first time, outperforming tuned machine-learning baselines in most settings, and its estimated intervention effects tracked those realized in natural experiments it had not seen. Its training scheme and three of its operators replicated in two fields withheld from development. Questions posed in natural language are compiled by a domain-specialized 27-billion-parameter language model into executable actions and answered as paired simulations with and without the intervention. The answers were rated 4.1 of 5 for faithfulness by an independent language-model judge. By revealing the latent dynamics of a research field and its response to interventions, research world models offer a new way to simulate and test research decisions before they are made.

Figures & tables

Explore similar work

CardsList
  1. Language Models as AI Research World Models

    Oct 8, 2026Zijun Wang, Zewen Liu, Minhua Lin +10LLM World ModelsAutonomous Research Agents

  2. ActTime: Action-Conditioned World Modeling for Time Series

    Oct 19, 2026Xinxing Zhou, Xiaojie Yuan, Yanlong Wen +1Action-Conditioned World ModelsModel-Based Planning

  3. CivWorldBench: Evaluating Language World Models in Structured Multi-Agent Sandbox Worlds

    Oct 12, 2026Ang Li, Haofei Yu, Zhengwei Tao +7LLM World ModelsWorld Model Evaluation