发表机构
Columbia University; University of California, Los Angeles; Northeastern University（哥伦比亚大学; 加州大学洛杉矶分校; 东北大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ARCANA是用于ARC-AGI-2推理的多智能体框架，将任务分解为感知、假设生成等步骤，智能体通过可微黑板通信，由元控制器调度。其设计结合程序搜索与校正，提升了抽象转换任务的推理效率和解决方案质量。
AI 中文摘要
我们提出了ARCANA，这是一个协作式多智能体框架，用于在严格的测试时间和硬件约束下解决ARC AGI 2任务。ARCANA将每个任务分解为迭代感知、假设生成、符号执行和反射式细化。一个感知基础智能体从原始网格构建以对象为中心的场景图，一个潜在程序策略提出不同的DSL程序，一个符号执行器在示范上验证候选程序，一个反射智能体为下一轮合成失败驱动的反馈。这些智能体通过共享的可微黑板进行通信，并由学习到的元控制器进行调度。该设计将结构化程序搜索与自适应多轮校正相结合，提高了在具有挑战性的抽象转换任务上的推理效率和解决方案质量。
英文摘要
We present ARCANA, a collaborative multi agent framework for solving ARC AGI 2 tasks under strict test time and hardware constraints. ARCANA decomposes each task into iterative perception, hypothesis generation, symbolic execution, and reflective refinement. A perceptual grounding agent builds object centric scene graphs from raw grids, a latent program policy proposes diverse DSL programs, a symbolic executor verifies candidates on demonstrations, and a reflective agent synthesizes failure driven feedback for the next turn. These agents communicate through a shared differentiable blackboard and are scheduled by a learned meta controller. The design combines structured program search with adaptive multi turn correction, improving reasoning efficiency and solution quality on challenging abstract transformation tasks.
