v1v2 (latest)
Out-of-Distribution Generalization in the ARC-AGI Domain: Comparing Execution-Guided Neural Program Synthesis and Test-Time Fine-Tuning
Main:7 Pages
4 Figures
Bibliography:1 Pages
6 Tables
Appendix:2 Pages
Abstract
We run a controlled compositional generalization experiment in the ARC-AGI domain: an open-world problem domain in which the ability to generalize out-of-distribution is, by design, an essential characteristic for success. We compare neural program synthesis and test-time fine-tuning approaches on this experiment. We find that execution-guided neural program synthesis outperforms all reference algorithms in its ability to compose novel solutions. Our empirical findings also suggest that the success of TTFT on ARC-AGI lies mainly in eliciting in-distribution knowledge that the LLM otherwise fails to rely on directly.
View on arXivComments on this paper
