# Executable World Models for ARC-AGI-3 in the Era of Coding Agents

arXiv: https://arxiv.org/abs/2605.05138 · HTML: https://mlsanity.com/paper/2605.05138/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 6 of its 13 references that are in the map.
- First posted on arXiv 6 May 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 6 of 6)

- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning](https://mlsanity.com/paper/2006.08381/) (2020)
- [WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment](https://mlsanity.com/paper/2402.12275/) (2024)
- [LILO: Learning Interpretable Libraries by Compressing and Documenting Code](https://mlsanity.com/paper/2310.19791/) (2023)
- [Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search](https://mlsanity.com/paper/2405.15383/) (2024)

## Built on by (most cited first, 14 of 14)

- [Code World Model: Coding Agent as World Brain](https://mlsanity.com/paper/2608.25927/) (2026)
- [Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning](https://mlsanity.com/paper/2608.27549/) (2026)
- [Prime Agent: A Self-Improving RLM Harness](https://mlsanity.com/paper/2608.23552/) (2026)
- [PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning](https://mlsanity.com/paper/2607.20064/) (2026)
- [OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3](https://mlsanity.com/paper/2607.01531/) (2026)
- [Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3](https://mlsanity.com/paper/2607.28287/) (2026)
- [Twin: Playing an Unknown Game with a Test-Time Digital Twin](https://mlsanity.com/paper/2608.14490/) (2026)
- [AGI Maze as a Benchmark Framework for World-Modeling Agents](https://mlsanity.com/paper/2607.00627/) (2026)
- [VISTA: A Visual Harness for Reasoning in an Interactive World](https://mlsanity.com/paper/2610.02200/) (2026)
- [AGI Maze Prediction Datasets: A Compact Benchmark for Learning World Dynamics with Transformers](https://mlsanity.com/paper/2609.02339/) (2026)
- [Schema: Discovering Unknown Environments via Agentic Program Induction](https://mlsanity.com/paper/2609.39140/) (2026)
- [Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks](https://mlsanity.com/paper/2610.11794/) (2026)
- [CivWorldBench: Evaluating Language World Models in Structured Multi-Agent Sandbox Worlds](https://mlsanity.com/paper/2610.16450/) (2026)
- [Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents](https://mlsanity.com/paper/2610.18082/) (2026)

## Abstract (arXiv)

We evaluate an initial coding-agent system for ARC-AGI-3 in which the agent maintains an executable Python world model, verifies it against previous observations, refactors it toward simpler abstractions as a practical proxy for an MDL-like simplicity bias, and plans through the model before acting. The system is intentionally direct: it uses a scripted controller, predefined world-model interfaces, verifier programs, and a plan executor, but no hand-coded game-specific logic. The agent-facing prompts, workspace, and controller contain no game-specific code, game-specific prompts, hand-coded heuristics, hidden solutions, or other game-specific information; the same agent and prompts are used across games. Because the coding agent has broad system access, we audit unintended information channels, describe earlier vulnerable harnesses, and explain how the current harness closes observed leakage channels while reducing benchmark-specific information exposure. We report results on the 25 public ARC-AGI-3 games. Each playthrough starts from a fresh agent instance and clean workspace, with no access to files or conversation state from earlier playthroughs. With GPT-5.5 high reasoning effort, the agent fully solved 15 games and achieved a mean per-game RHAE of 58.12%. With GPT-5.4 high reasoning effort, it fully solved 8 games and achieved a mean per-game RHAE of 41.29%. Performance on the private validation set, which is not yet available to us, remains to be tested. Overall, the results provide preliminary evidence that verifier-driven executable world models are a promising approach for ARC-AGI-3 agents. Full run artifacts are released with the code at https://github.com/astroseger/arc-3-agents-baseline1.