@article{pbebenchamultistepprogrammingbyexamples, title = {PBEBench: A Multi-Step Programming by Examples Reasoning Benchmark inspired by Historical Linguistics}, author = {Atharva Naik and Darsh Agrawal and Manav Kapadnis and Yuwei An and Yash Mathur and Carolyn Rose and David Mortensen}, year = {2025}, eprint = {2505.23126}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.23126v1}, }