面向 ARC-AGI 的符号化演化求解器：首个提交至主赛的纯符号演化程序合成方法
Ceci n'est pas une pipe -- Toward a Symbolic Solver for the Abstraction and Reasoning Corpus Using Evolutionary Computation
AI 导读
研究者提出首个提交至 ARC-AGI-2 主赛的完全符号化、基于演化算法的程序合成方法，此前演化算法在主赛中明显缺席。方法将网格解析器与输出投影器随程序共同演化，使任务专用语言在合成过程中涌现，并将符号扎根于认知心理学的核心知识理论；同时引入对象感知的适应度函数，对部分正确的输出按超出像素级差异的标准评分。
正文 · 原文
Abstract:The Abstraction and Reasoning Corpus (ARC) is a benchmark designed to assess the capability of Artificial Intelligence (AI) systems to generalize starting from a few samples, a task humans excel at. The ARC-AGI contests held since 2020 have been the focus of intense competition, with participants proposing approaches ranging from traditional symbolic AI to Transformer architectures. Despite a long history of successes, evolutionary algorithms (EAs) were notably absent from the approaches appearing in the main contest. As score-and-search program synthesis approaches, EAs suffer from issues related to choosing the proper representation in the Domain-Specific Language applied to the problem (for example, pixel-level or object-level), and distinguishing between two candidate solutions producing the same outputs. In this work, we present the first fully symbolic, evolutionary-based program synthesis approach submitted to the ARC-AGI-2 main contest. The main contributions are: evolving the grid parser and the output projector together with the program that transforms the grid, so that a task-specific language emerges during program synthesis; grounding the symbols the parser can extract in core knowledge theory from cognitive psychology; and an object-aware fitness that grades partially correct outputs beyond pixel-level discrepancies.
| Comments: | Submitted to the ARC Prize 2026 Paper Track (Fairly Symbolic) |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.13831 [cs.AI] |
| (or arXiv:2611.13831v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13831 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Giovanni Squillero [view email]
[v1]
Tue, 10 Nov 2026 09:57:01 UTC (1,403 KB)
来源：arXiv cs.AI · arxiv.org