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

论文用 textual baseline、flexible executable world model、带 scheduled simplification 的 executable model、以及 fixed-interface replay verification 四个 Codex-based agent 做消融。主实验覆盖 gpt-5.4 与 gpt-5.5 的 high/xhigh effort；最稳定的结果是更强模型和更高 effort 都显著改善，组件贡献则随设置变化。gpt-5.6-sol 跟进让 verification 变体全解公开 games、约 99% RHAE，但作者明确把它限定为公开集饱和而非 held-out 证明。