面向组合与可解释认知推理的多阶段规则链式框架
原标题：A Multi-Stage Rule-Chaining Framework for Compositional and Interpretable Cognitive Reasoning
AI 摘要
该论文提出一个多阶段规则链式框架，用于在ARC-AGI-2基准上进行组合式与可解释的认知推理。框架整合三个互补求解器：确定性规则发现、模式组合引擎和结构抽象层，按渐进回退层级顺序运行并复用先前推理轨迹。在1000个任务中通过995个训练任务，并在240个ARC-AGI-2测试任务中解决230个，整体准确率超过95%。
正文节选
A Multi-Stage Rule-Chaining Framework for Compositional and Interpretable Cognitive Reasoning Abstract The Abstraction and Reasoning Corpus (ARC) benchmarks cognitive generalization—the ability to infer and apply abstract rules from limited examples. This paper presents a multi-stage rule-chaining framework that performs compositional reasoning across symbolic, structural, and conceptual levels. The framework integrates three complementary solvers: (1) a deterministic rule discovery module that