@inproceedings{yanfangzhou-etal-2025-m2pa,
title = "{M}2{PA}: A Multi-Memory Planning Agent for Open Worlds Inspired by Cognitive Theory",
author = "Zhou, Yanfang and
Li, Xiaodong and
Liu, Yuntao and
Zhao, Yongqiang and
Wang, Xintong and
Li, Zhenyu and
Tian, Jinlong 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.1191/",
doi = "10.18653/v1/2025.findings-acl.1191",
pages = "23204--23220",
ISBN = "979-8-89176-256-5",
abstract = "Open-world planning poses a significant challenge for general artificial intelligence due to environmental complexity and task diversity, especially in long-term tasks and lifelong learning. Inspired by cognitive theories, we propose M2PA, an open-world multi-memory planning agent. M2PA innovates by combining Large Language Models (LLMs) with human-like multi-memory systems, aiming to fully leverage the strengths of both while mitigating their respective limitations. By integrating the expansive world knowledge and language processing capabilities of LLMs with the perception and experience accumulation abilities of the human memory system, M2PA exhibits situation awareness, and experience generalization capabilities, as well as the potential for lifelong learning. In experiments, M2PA significantly outperforms current state-of-the-art agents across 50 Minecraft tasks in zero-shot learning. In exploratory lifelong learning experiments, M2PA demonstrates its continuous learning ability, achieving a \textbf{38.33{\%}} success rate in the ``ObtainDiamond'' task. Our findings provide a novel paradigm for constructing more effective agents in open-world environments."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yanfangzhou-etal-2025-m2pa">
<titleInfo>
<title>M2PA: A Multi-Memory Planning Agent for Open Worlds Inspired by Cognitive Theory</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">Xiaodong</namePart>
<namePart type="family">Li</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">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">Zhenyu</namePart>
<namePart type="family">Li</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">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>Open-world planning poses a significant challenge for general artificial intelligence due to environmental complexity and task diversity, especially in long-term tasks and lifelong learning. Inspired by cognitive theories, we propose M2PA, an open-world multi-memory planning agent. M2PA innovates by combining Large Language Models (LLMs) with human-like multi-memory systems, aiming to fully leverage the strengths of both while mitigating their respective limitations. By integrating the expansive world knowledge and language processing capabilities of LLMs with the perception and experience accumulation abilities of the human memory system, M2PA exhibits situation awareness, and experience generalization capabilities, as well as the potential for lifelong learning. In experiments, M2PA significantly outperforms current state-of-the-art agents across 50 Minecraft tasks in zero-shot learning. In exploratory lifelong learning experiments, M2PA demonstrates its continuous learning ability, achieving a 38.33% success rate in the “ObtainDiamond” task. Our findings provide a novel paradigm for constructing more effective agents in open-world environments.</abstract>
<identifier type="citekey">yanfangzhou-etal-2025-m2pa</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1191</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1191/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>23204</start>
<end>23220</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T M2PA: A Multi-Memory Planning Agent for Open Worlds Inspired by Cognitive Theory
%A Zhou, Yanfang
%A Li, Xiaodong
%A Liu, Yuntao
%A Zhao, Yongqiang
%A Wang, Xintong
%A Li, Zhenyu
%A Tian, Jinlong
%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-m2pa
%X Open-world planning poses a significant challenge for general artificial intelligence due to environmental complexity and task diversity, especially in long-term tasks and lifelong learning. Inspired by cognitive theories, we propose M2PA, an open-world multi-memory planning agent. M2PA innovates by combining Large Language Models (LLMs) with human-like multi-memory systems, aiming to fully leverage the strengths of both while mitigating their respective limitations. By integrating the expansive world knowledge and language processing capabilities of LLMs with the perception and experience accumulation abilities of the human memory system, M2PA exhibits situation awareness, and experience generalization capabilities, as well as the potential for lifelong learning. In experiments, M2PA significantly outperforms current state-of-the-art agents across 50 Minecraft tasks in zero-shot learning. In exploratory lifelong learning experiments, M2PA demonstrates its continuous learning ability, achieving a 38.33% success rate in the “ObtainDiamond” task. Our findings provide a novel paradigm for constructing more effective agents in open-world environments.
%R 10.18653/v1/2025.findings-acl.1191
%U https://aclanthology.org/2025.findings-acl.1191/
%U https://doi.org/10.18653/v1/2025.findings-acl.1191
%P 23204-23220
Markdown (Informal)
[M2PA: A Multi-Memory Planning Agent for Open Worlds Inspired by Cognitive Theory](https://aclanthology.org/2025.findings-acl.1191/) (Zhou et al., Findings 2025)
ACL
- Yanfang Zhou, Xiaodong Li, Yuntao Liu, Yongqiang Zhao, Xintong Wang, Zhenyu Li, Jinlong Tian, and Xinhai Xu. 2025. M2PA: A Multi-Memory Planning Agent for Open Worlds Inspired by Cognitive Theory. In Findings of the Association for Computational Linguistics: ACL 2025, pages 23204–23220, Vienna, Austria. Association for Computational Linguistics.