Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?

arXiv:2607.15439 · cs.AI · Submitted 2026-07-16 · Read on arXiv

cs.AI

Submitted: 2026-07-16

Updated: 2026-08-27

Code: https://github.com/astroseger/arc-3-agents-baseline1

Terminology

• Verification — 92× in this paper · explained in 2 episodes
• World Model — 81× in this paper · explained in 7 episodes
• Verifier — 15× in this paper · explained in 2 episodes
• Benchmark — 11× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Core — 5× in this paper · explained in 2 episodes
• Ontology — 5× in this paper · explained in 2 episodes
• Abstraction — 4× in this paper · explained in 1 episode
• Generalization — 2× in this paper · explained in 13 episodes
• Minimum Description Length — 2× in this paper
• Relative Human Action Efficiency — 2× in this paper
• Ablation study — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Agent Harness — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence
• AGI Maze as a Benchmark Framework for World-Modeling Agents
• Executable World Models for ARC-AGI-3 in the Era of Coding Agents
• Graph-Based Exploration for ARC-AGI-3 Interactive Reasoning Tasks
• Workspace Optimization: How to Train Your Agent

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection