@inproceedings{shin-etal-2026-graphmind,
    title = "{G}raph{M}ind: {LLM}s as Dynamic Knowledge Builders for Sequential Decision-Making",
    author = "Shin, Sunguk  and
      Lee, Hayeong  and
      Seo, Jun Ho  and
      Lee, Jinho  and
      Kim, Myunsoo  and
      Chang, Minsuk  and
      Lee, Byung-Jun",
    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.1651/",
    pages = "32985--33007",
    ISBN = "979-8-89176-395-1",
    abstract = "While the reasoning capabilities of large language models (LLMs) have advanced considerably, efficiently internalizing and leveraging new information in dynamically interactive environments remains a significant challenge. This limitation is particularly pronounced in partially observable environments, which require agents to manage long-term memory and perform effective exploration under incomplete information. To address this, we propose an LLM agent architecture that integrates a knowledge graph as a graph-based memory module. The agent incrementally constructs the knowledge graph through environmental interactions and retrieves relevant information to generate efficient plans. We evaluate our approach in complex navigation tasks specifically designed to present long-horizon and partially observable challenges. Experimental results demonstrate that incorporating a self-extending memory module significantly enhances the performance and efficiency of the LLM{'}s planning capabilities."
}