@inproceedings{xu25neurips, title = {TheAgentCompany: Benchmarking {LLM} Agents on Consequential Real World Tasks}, author = {Frank F. Xu and Yufan Song and Boxuan Li and Yuxuan Tang and Kritanjali Jain and Mengxue Bao and Zora Zhiruo Wang and Xuhui Zhou and Zhitong Guo and Murong Cao and Mingyang Yang and Hao Yang Lu and Amaad Martin and Zhe Su and Leander Melroy Maben and Raj Mehta and Wayne Chi and Lawrence Keunho Jang and Yiqing Xie and Shuyan Zhou and Graham Neubig}, booktitle = {Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track}, address = {San Diego, USA}, month = {December}, url = {https://arxiv.org/abs/2412.14161}, year = {2025} }