cs.LGNov 9, 2026

How Many Exposures Does a World Model Need? Learning Unseen Game Mechanics at Test Time

Authors: Ku Onoda, Haruto Kawano, Shota Takashiro, Kohei Hayashi

Organizations: Third Intelligence, Inc. · The University of Tokyo

Abstract

World models enable agents to plan and learn from imagined experience, but in an unfamiliar environment they must learn its mechanics from limited interaction. A mechanic is a rule for how an action or an interaction changes part of the environment. Each occurrence of a mechanic that the model observes is one exposure. We ask how many exposures a world model needs to predict the effects of a new environment's mechanics. We address this question on ARC-AGI-3, a benchmark of interactive games defined by their programs. We introduce MechEval, which labels 69 recurring mechanics across 20 games from these programs. It scores each prediction on the cells the mechanic changes at each exposure. As a test bed, we build WARC (World model for ARC-AGI-3), a 35M-parameter vision transformer that is pretrained on other games and updates all of its parameters after each transition. On held-out games, WARC learns to predict four in five mechanics with at least 80% accuracy on the cells they change and keeps that accuracy to the end of the recordings. Half of them reach that accuracy within about 80 exposures, in a single play of the game, and without updates only one in seven does at all. In closed-loop play on the public games, WARC-Agent, which pairs WARC with a fixed graph explorer, triples the explorer's official efficiency score from 0.15 to 0.46, mostly through test-time training. On the hidden games of the Kaggle leaderboard, our entry scores 0.20.

Figures & tables

Appendix figures & tables23 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Aug 14, 2026

Twin: Playing an Unknown Game with a Test-Time Digital Twin

We present a Test-time World-model Inference (Twin) system, in which a frontier coding agent writes an executable world model for completing continual learning tasks, such as ARC-AGI-3 games. Traditional approaches hand-engineer such models, one custom design per task. Each game hides its rules and goal, and our system constructs them from simulation and interaction alone. Its inductive prior over grid games is strong enough to recover the true transitions of the game and the goal on nearly all levels. Replay validation happens in a twin world model. The harness enforces that an action is not made until the program reproduces every previous observed game transition. Each mismatch between a world model prediction and the actual action result becomes a counterexample that is used to repair the world model. Twin clears 179 out of 183 levels (97.8%), and does so more efficiently than humans in 158 out of 179 levels (88.3%). The system infers the goal before any reward on 156 of the levels it clears (87.2%), and in the remaining levels automatically discovers the goal by search. The benchmark scores completion and action efficiency, between 0 and 100, against humans playing each game for the first time. Played directly, the base model scores only 7.8%; an off-the-shelf harness increases it to 61.1%, whereas our twin world model increases the same base model to 93.3%, clearing 23 out of 25 games. Building a usable world model is simpler than anticipated, whereas the harder problem is inferring the right goal.
May 7, 2026

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

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.
Sep 27, 2026

Does Learning to Predict the World Help Agents Act? Auditing World-Model Post-Training

Predicting how an environment will change before acting is a natural route to better decision making for agents. Recent post-training methods therefore require agents to predict the next observation and turn that prediction into a reward or a direct supervision signal, which is called world model. Existing next-observation training methods help the agent to learn the environmental content. However, they additionally involve an optimization process, which may introduce several effects other than learning to predict the world. Consequently, where the performance gain comes from during the training process remains an open question. We answer this research question through replacing true next-observation targets with in-distribution mismatched observations during the training process. Across two interactive text environments, mismatched targets lower prediction accuracy by 15.3-61.6% relative to ground-truth targets, yet retain substantial task gains over the base model. Compared with the base model, trained models consider more candidate actions and exhibit less looping. We also introduce a setting that replaces prediction-based rewards with independent random signals. This training expands task coverage (pass@64) even when the reward carries no environment information. We also generalize this finding to VisualWebArena, where random-reward training raises pass@64 by 14.3% relative to the base model, without observation-matching rewards or an external multimodal teacher for reward construction.