@article{agentrewardbenchevaluatingautomatic, title = {AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories}, author = {Xing Han Lù and Amirhossein Kazemnejad and Nicholas Meade and Arkil Patel and Dongchan Shin and Alejandra Zambrano and Karolina Stańczak and Peter Shaw and Christopher J. Pal and Siva Reddy}, year = {2025}, eprint = {2504.08942}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.08942v1}, }