ARC-GEN：面向抽象与推理语料库的模仿式程序化基准生成器
ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus
AI总结：
本文提出ARC-GEN，一个开源程序化生成器，通过穷尽且模仿性地扩展原始ARC-AGI训练数据集，解决其演示集规模限制问题，并应用于验证2025年Google Code Golf锦标赛提交程序的正确性。
摘要：
抽象与推理语料库（Abstraction and Reasoning Corpus）仍然是追踪通用人工智能进展的最具吸引力和挑战性的基准之一。与其他旨在评估智能体特定任务技能或积累知识的数据集不同，ARC-AGI套件专门用于衡量技能获取效率，这一特征（到目前为止）即使在最先进的机器学习系统中也一直缺乏。对于需要大量任务内示例的算法，ARC-AGI施加的一个重大限制是其演示集的基数适中，每个任务包含少量指定相应转换的<输入，输出>网格。为了扩充可用样本对的空间，本文介绍了ARC-GEN，这是一个开源程序化生成器，旨在尽可能忠实地扩展原始ARC-AGI训练数据集。与以往的努力不同，我们的生成器既具有穷尽性（涵盖全部四百个任务），又具有模仿性（更紧密地尊重初始ARC-AGI-1版本中体现的分布特性和特征）。我们还讨论了使用此生成器建立静态基准套件，以验证提交给2025年Google Code Golf锦标赛的程序的正确性。
英文摘要：
The Abstraction and Reasoning Corpus remains one of the most compelling and challenging benchmarks for tracking progress toward achieving Artificial General Intelligence. In contrast to other evaluation datasets designed to assess an agent's task-specific skills or accumulated knowledge, the ARC-AGI suite is specifically targeted at measuring skill acquisition efficiency, a trait that has (so far) been lacking in even the most sophisticated machine learning systems. For algorithms that require extensive intra-task exemplars, a significant constraint imposed by ARC-AGI is the modest cardinality of its demonstration set, comprising a small number of $\langle$ input, output $\rangle$ grids per task specifying the corresponding transformation. To embellish the space of viable sample pairs, this paper introduces ARC-GEN, an open-source procedural generator aimed at extending the original ARC-AGI training dataset as faithfully as possible. Unlike prior efforts, our generator is both exhaustive (covering all four-hundred tasks) and mimetic (more closely honoring the distributional properties and characteristics embodied in the initial ARC-AGI-1 release). We also discuss the use of this generator in establishing a static benchmark suite to verify the correctness of programs submitted to the 2025 Google Code Golf Championship.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
