Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2
把LLM当成编码器不算本事,能像程序猿一样逐行debug才是真功夫。这个ABPR方法用Prolog做语义级反演调试,直接把ARC-AGI-2的准确率拉到98%,抽象推理领域的新里程碑。
arXiv:2603.20334v3 Announce Type: replace-cross Abstract: In high-complexity abstract reasoning, a system must infer a latent rule from a few examples…