Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

AIPR assessment

Problem difficulty: this is a highly saturated and rapidly expanding survey problem, with overlapping literatures across RL, video generation, agents, social simulation, and scientific discovery. The paper’s strongest strengths reinforce each other, the taxonomy, regime split, and benchmark tables jointly create a usable map of a messy field, and the evaluation package gives the framework practical traction. The weaknesses also compound, because the work is intentionally ambitious and partly phi

Abstract

As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment dynamics becomes a central bottleneck. Agents that manipulate objects, navigate software, coordinate with others, or design experiments require predictive environment models, yet the term world model carries different meanings across research communities. We introduce a "levels x laws" taxonomy organized along two axes. The first defines three capability levels: L1 Predictor, which learns one-step local transition operators; L2 Simulator, which composes them into multi-step, action-conditioned rollouts that respect domain laws; and L3 Evolver, which autonomously revises its own model when predictions fail against new evidence. The second identifies four governing-law regimes: physical, digital, social, and scientific. These regimes determine what constraints a world model must satisfy and where it is most likely to fail. Using this framework, we synthesize over 400 works and summarize more than 100 representative systems spanning model-based reinforcement learning, video generation, web and GUI agents, multi-agent social simulation, and AI-driven scientific discovery. We analyze methods, failure modes, and evaluation practices across level-regime pairs, propose decision-centric evaluation principles and a minimal reproducible evaluation package, and outline architectural guidance, open problems, and governance challenges. The resulting roadmap connects previously isolated communities and charts a path from passive next-step prediction toward world models that can simulate, and ultimately reshape, the environments in which agents operate. Code and resources are available at: https://github.com/matrix-agent/awesome-agentic-world-modeling.

Score Breakdown

More from this week

• How Hard is it to Decide if a Fact is Relevant to a Query?
• Railway Artificial Intelligence Learning Benchmark (RAIL-BENCH): A Benchmark Suite for Perception in the Railway Domain
• On first-order model checking parameterized by the number of variables
• Entrywise Low-Rank Approximation and Matrix \(p \rightarrow q\) Norms via Global Correlation Rounding
• Cuts and Gauges for Submodular Width

More in AI

• GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines
• The CIFAR Synthetic Evidence Corpus for Detecting AI-Generated Evidence
• PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects
• SCOPE: Cost-Efficient Model Selection for Compound AI Systems under Quality Constraints
• Context Features Are Cheap: Rank-Aware Decomposition for Efficient Feature Interaction in Recommender Systems