@inproceedings{yanfangzhou-etal-2025-metagent,
    title = "Metagent-{P}: A Neuro-Symbolic Planning Agent with Metacognition for Open Worlds",
    author = "YanfangZhou, YanfangZhou  and
      Liu, Yuntao  and
      Li, Xiaodong  and
      Zhao, Yongqiang  and
      Wang, Xintong  and
      Tian, Jinlong  and
      Li, Zhenyu  and
      Xu, Xinhai",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/mtsummit-25-ingestion/2025.findings-acl.1169/",
    doi = "10.18653/v1/2025.findings-acl.1169",
    pages = "22747--22764",
    ISBN = "979-8-89176-256-5",
    abstract = "The challenge of developing agents capable of open-world planning remains fundamental to artificial general intelligence (AGI). While large language models (LLMs) have made progress with their vast world knowledge, their limitations in perception, memory, and reliable reasoning still hinder LLM-based agents from achieving human-level performance in long-term tasks. Drawing inspiration from human cognitive-metacognitive collaboration, we propose \textbf{Metagent-P}, integrating the world knowledge of LLMs, the symbolic reasoning capabilities of cognitive architectures, and the self-reflection characteristic of metacognition to construct a ``planning-verification-execution-reflection'' framework. Metagent-P improves experience utilization through multimodal memory integration. It uses a neural-symbolic hierarchical representation structure to ensure the plan{'}s reasoning correctness in advance. Finally, it actively adapts the agent to dynamic environments through monitoring, evaluation, and regulation mechanisms. Experimental results show Metagent-P significantly outperforms current state-of-the-art methods in Minecraft. In long-term tasks, Metagent-P reduces the average replanning counts by \textbf{34{\%}} and exceeds the average human success rate by \textbf{18.96{\%}}. Additionally, Metagent-P also demonstrates self-evolution through step-by-step open-world exploration."
}