Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI

ArXi:2507.14172v2 Announce Type: replace-cross Many program synthesis tasks prove too challenging for even state-of-the-art language models to solve in single attempts. Search-based evolutionary methods offer a promising alternative by exploring solution spaces iteratively, but their effectiveness remain limited by the fixed capabilities of the underlying generative model. We propose SOAR, a method that learns program synthesis by integrating language models into a self-improving evolutionary loop.