@inproceedings{qiao-etal-2025-agentic,
    title = "Agentic Knowledgeable Self-awareness",
    author = "Qiao, Shuofei  and
      Qiu, Zhisong  and
      Ren, Baochang  and
      Wang, Xiaobin  and
      Ru, Xiangyuan  and
      Zhang, Ningyu  and
      Chen, Xiang  and
      Jiang, Yong  and
      Xie, Pengjun  and
      Huang, Fei  and
      Chen, Huajun",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.619/",
    pages = "12601--12625",
    ISBN = "979-8-89176-251-0",
    abstract = "Large Language Models (LLMs) have achieved considerable performance across various agentic planning tasks. However, traditional approaches adopt a ``flood irrigation'' methodology that indiscriminately injects gold trajectories, external feedback, and domain knowledge into agent models. This practice overlooks the fundamental human cognitive principle of self-awareness - the ability to dynamically assess situational demands and strategically employ resources during decision-making. We propose $\textbf{Agentic Knowledgeable Self-awareness}$ to address this gap, a novel paradigm enabling LLM-based agents to autonomously regulate knowledge utilization. Specifically, we propose $\texttt{KnowSelf}$, a data-centric approach that applies agents with $\texttt{know}$ledgeable $\texttt{self}$-awareness like humans. Concretely, we devise a heuristic situation judgement criterion to mark special tokens on the agent{'}s self-explored trajectories for collecting training data. Through a two-stage training process, the agent model can switch between different situations by generating specific special tokens, achieving optimal planning effects with minimal costs. Our experiments demonstrate that can outperform various strong baselines on different tasks and models with minimal use of external knowledge."
}