@inproceedings{yanfangzhou-etal-2025-metagent,
title = "Metagent-{P}: A Neuro-Symbolic Planning Agent with Metacognition for Open Worlds",
author = "Zhou, Yanfang 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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yanfangzhou-etal-2025-metagent">
<titleInfo>
<title>Metagent-P: A Neuro-Symbolic Planning Agent with Metacognition for Open Worlds</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanfang</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuntao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongqiang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xintong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinlong</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinhai</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<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 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 34% and exceeds the average human success rate by 18.96%. Additionally, Metagent-P also demonstrates self-evolution through step-by-step open-world exploration.</abstract>
<identifier type="citekey">yanfangzhou-etal-2025-metagent</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1169</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1169/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>22747</start>
<end>22764</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Metagent-P: A Neuro-Symbolic Planning Agent with Metacognition for Open Worlds
%A Zhou, Yanfang
%A Liu, Yuntao
%A Li, Xiaodong
%A Zhao, Yongqiang
%A Wang, Xintong
%A Tian, Jinlong
%A Li, Zhenyu
%A Xu, Xinhai
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F yanfangzhou-etal-2025-metagent
%X 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 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 34% and exceeds the average human success rate by 18.96%. Additionally, Metagent-P also demonstrates self-evolution through step-by-step open-world exploration.
%R 10.18653/v1/2025.findings-acl.1169
%U https://aclanthology.org/2025.findings-acl.1169/
%U https://doi.org/10.18653/v1/2025.findings-acl.1169
%P 22747-22764
Markdown (Informal)
[Metagent-P: A Neuro-Symbolic Planning Agent with Metacognition for Open Worlds](https://aclanthology.org/2025.findings-acl.1169/) (Zhou et al., Findings 2025)
ACL
- Yanfang Zhou, Yuntao Liu, Xiaodong Li, Yongqiang Zhao, Xintong Wang, Jinlong Tian, Zhenyu Li, and Xinhai Xu. 2025. Metagent-P: A Neuro-Symbolic Planning Agent with Metacognition for Open Worlds. In Findings of the Association for Computational Linguistics: ACL 2025, pages 22747–22764, Vienna, Austria. Association for Computational Linguistics.