@inproceedings{xi-etal-2026-c,
    title = "{C}-World: A Computer Use Agent Environment Creator",
    author = "Xi, Ziqiao  and
      Liang, Shuang  and
      Liu, Qi  and
      Zhang, Jiaqing  and
      Peng, Letian  and
      Nan, Fang  and
      Nayim, Meshal  and
      Zhang, Tianhui  and
      Mundada, Rishika  and
      Qin, Lianhui  and
      Huang, Biwei  and
      Zhou, Kun",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.2001/",
    pages = "43202--43216",
    ISBN = "979-8-89176-390-6",
    abstract = "To close the gap between LLM-based agents and humans in planning and reasoning, agents need large-scale, diverse environments for continuous learning{---}yet building such environments is itself prohibitively expensive. We present C-World, an environment creation system that enables users to build agent environments on demand. We define a complete agent environment through four components: an Action Space of 5,571 format-unified tools across 204 common applications, a Task Distribution engine that synthesizes long-horizon workflows with wild constraints, a Transition Function implemented as a state controller that injects realistic failures and perturbations, and a Reward Signal combining verifiable metrics with LLM-based judgment. C-World operates in two modes: a realistic mode grounded in live API execution, and a synthesized mode powered by the World Engine, which approximates tool behavior without live service access, enabling scalable environment creation{---}including environments for domains and tools that do not yet exist in the real world. Evaluation of nine state-of-the-art LLMs reveals that planning ability is uniformly strong but execution remains the bottleneck, and that constraint following{---}not tool invocation{---}is the dominant failure mode. The World Engine achieves Spearman $\rho = 0.883$ ranking correlation with real execution, and fine-tuning on just 1,170 C-World trajectories outperforms baselines trained on 119k samples, demonstrating C-World{'}s dual value as a rigorous evaluation environment and a scalable data engine. Our code and data are available at https://ziqiao-git.github.io/C-World/."
}