AGWM: Affordance-Grounded World Models for Environments with Compositional Prerequisites

Computer Science > Artificial Intelligence [Submitted on 7 May 2026] AGWM: Affordance-Grounded World Models for Environments with Compositional Prerequisites Qinshi Zhang (1), Weipeng Deng (2), Zhihan Jiang (3), Jiaming Qu (4), Qianren Li (5), Weitao Xu (5), Ray LC (5) ((1) University of California, San Diego, (2) University of Hong Kong, (3) Columbia University, (4) Amazon, (5) City University of Hong Kong) In model-based learning, the agent learns behaviors by simulating trajectories based on world model predictions. Standard world models typically learn a stationary transition function that maps states and actions to next states, when an action and an outcome frequently co-occur in training data, the model tends to internalize this correlation as a general causal rule while ignoring action preconditions. In interactive environments, however, agent actions can reshape the future affordance space. At each timestep, an action may becomes executable only after its prerequisites are met, or non-executable when they are destroyed. We term such events structure-changing events (SC events). As a result, a conventional world model often fails to determine whether a given action is executable in the current state, especially in multi-step predictions. Each imagined step is conditioned on an incorrect affordance state, and therefore the prediction error compounds over the rollout horizon. In this paper, we propose AGWM (Affordance-Grounded World Model), which learns an abstract affordance structure represented as a DAG of prerequisite dependencies to explicitly track the dynamic executability of actions. Experiments on game-based simulated environments demonstrate the effectiveness of our method by achieving lower multi-step prediction error, better generalization to novel configurations, and improved interpretability. Comments: 16 pages, 3 figures, 4 tables. Appendix on pages 11-16 (main text is self-contained) Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG) ACM classes: I.2.6; I.2.8 Cite as: arXiv:2605.06841 [cs.AI]   (or arXiv:2605.06841v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2605.06841 Focus to learn more Submission history From: Qinshi Zhang [view email] [v1] Thu, 7 May 2026 18:46:44 UTC (5,119 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)