A Multi-Stage Rule-Chaining Framework for Compositional and Interpretable Cognitive Reasoning
A Multi-Stage Rule-Chaining Framework for Compositional and Interpretable Cognitive Reasoning
一种用于组合式与可解释认知推理的多阶段规则链框架
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.
摘要： 抽象与推理语料库（ARC）旨在基准测试认知泛化能力，即从有限示例中推断并应用抽象规则的能力。本文提出了一种多阶段规则链框架，能够在符号、结构和概念层面执行组合式推理。
The framework integrates three complementary solvers: (1) a deterministic rule discovery module that induces atomic transformations through geometric, color, and object-based analysis; (2) a pattern-composition engine that reconstructs outputs via block merging, repetition, and spatial heuristics; and (3) a structural abstraction layer that infers hierarchical and nested relationships across grids.
该框架集成了三个互补的求解器：(1) 一个确定性规则发现模块，通过几何、颜色和基于对象的分析来归纳原子变换；(2) 一个模式组合引擎，通过块合并、重复和空间启发式方法重构输出；以及 (3) 一个结构抽象层，用于推断网格间的层次化和嵌套关系。
These solvers operate sequentially within a progressive fallback hierarchy, where each stage reuses prior reasoning traces to enhance interpretability and generalization. Training passed for 995 tasks out of 1000, further evaluated on 105 tasks out of 120 and solved 230 test tasks out of 240 ARC-AGI-2 tasks.
这些求解器在一个渐进式回退层级中顺序运行，每个阶段都会复用先前的推理轨迹，以增强可解释性和泛化能力。在训练阶段，系统在 1000 个任务中通过了 995 个，随后在 120 个任务中评估了 105 个，并在 240 个 ARC-AGI-2 测试任务中成功解决了 230 个。
The system achieved strong coverage across deterministic, compositional, and abstract categories, demonstrating an overall accuracy exceeding 95 percent. The proposed architecture bridges symbolic reasoning and pattern synthesis, providing interpretable insight into cognitive generalization.
该系统在确定性、组合式和抽象类别中实现了强大的覆盖率，整体准确率超过 95%。所提出的架构架起了符号推理与模式合成之间的桥梁，为认知泛化提供了可解释的洞察。
The results suggest that rule chaining and hierarchical composition can advance machine reasoning toward transparent, human-aligned abstraction without relying on task-specific tuning.
研究结果表明，规则链和层次化组合可以推动机器推理向透明、符合人类逻辑的抽象方向发展，且无需依赖针对特定任务的调优。