@inproceedings{fang-etal-2026-towards,
    title = "Towards General Agentic Intelligence via Environment Scaling",
    author = "Fang, Runnan  and
      Cai, Shihao  and
      Li, Baixuan  and
      Wu, Jialong  and
      Li, Guangyu  and
      Yin, Wenbiao  and
      Wang, Xinyu  and
      Wang, Xiaobin  and
      Su, Liangcai  and
      Zhang, Zhen  and
      Wu, Shibin  and
      Tao, Zhengwei  and
      Jiang, Yong  and
      Xie, Pengjun  and
      Zhang, Ningyu  and
      Huang, Fei  and
      Zhang, Wentao  and
      Zhou, Jingren",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.872/",
    pages = "17610--17621",
    ISBN = "979-8-89176-395-1",
    abstract = "Advanced agentic intelligence is a prerequisite for deploying Large Language Models in practical, real-world applications. Diverse real-world APIs demand precise, robust function-calling intelligence, which needs agents to develop these capabilities through interaction in varied environments. The breadth of function-calling competence is closely tied to the diversity of environments in which agents are trained. In this work, we scale up environments as a step towards advancing general agentic intelligence. This gives rise to two central challenges: (i) how to scale environments in a principled manner, and (ii) how to effectively train agentic capabilities from experiences derived through interactions with these environments. To address these, we design a scalable framework that automatically constructs heterogeneous environments that are fully simulated, broadening the space of function-calling scenarios. We further adapt a two-phase agent fine-tuning strategy: first endowing agents with fundamental agentic capabilities, then specializing them for domain-specific contexts. Extensive experiments on agentic benchmarks, -bench, -Bench, and ACEBench, demonstrate that our trained model, AgentScaler, significantly enhances the models' function-calling capability."
}