AI 中文总结
本文结合LLM生成初始程序与遗传算法演化，通过紧凑DSL提升ARC-AGI-2任务解决率，从3.3%提升至10.0%，证明遗传搜索能有效增强LLM输出。
AI 中文摘要
LLM能够为ARC-AGI-2任务生成程序，但提供的计算资源仅允许少量尝试来生成、调试和验证解决方案。遗传算法可以搜索并测试更多程序，但随机搜索很少能在解空间的有用邻域内起步。我们通过一种紧凑的领域特定语言（DSL）将这两种方法结合起来。首先，一个量化的Qwen3.5-4B LLM为每个ARCAGI-2任务生成一组初始程序。然后，我们使用这些程序作为初始种群的种子，并利用遗传算法将这些程序演化至给定任务的解决方案。该DSL的设计确保每个变异后的程序仍然有效且可执行。LLM提出的初始程序在ARC-2公开评估集的前60个任务中解决了2个（3.3%）。遗传算法额外解决了4个，总共得到6个正确的测试输出（10.0%）。如果我们尝试在没有LLM种子播种的情况下使用演化解决方案，则完全无法得到任何解决方案。结果表明，遗传搜索可以改进LLM生成的程序，并产生额外的正确解决方案。
英文摘要
LLMs can generate programs for ARC-AGI-2 tasks, but the provided compute only allows a small number of attempts to generate, debug and validate solutions. Genetic algorithms can search and test many more programs, but random search rarely starts in a useful neighborhood of the solution space. We combine the two methods through a compact domain specific language (DSL). First, a quantized Qwen3.5-4B LLM generates an initial set of programs for each ARCAGI-2 task. Then, we use those programs to seed an initial population of starting programs, and use genetic algorithms to evolve these programs towards a solution to the given task. The DSL is designed such that every mutated program remains valid and can be executed. The initial programs proposed by the LLM solve 2 (3.3%) of the first 60 tasks of the ARC-2 public evaluation set. The genetic algorithm solves an additional 4, giving 6 correct test outputs in total (10.0%). If we try using evolving solutions without this LLM seeding, we do not arrive at any solutions at all. The results show that genetic search can improve programs generated by LLMs and produce additional correct solutions.
