Lune

ACL Findings2026

GraphMind: LLMs as Dynamic Knowledge Builders for Sequential Decision-Making

Sunguk Shin, Hayeong Lee, JunHo Seo, Jinho Lee, Myunsoo Kim, Minsuk Chang, Byung-Jun Lee

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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning cites ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
  • Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach cites ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on12

  1. Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran et al.NeurIPS 2023 · 5,068 citations
  2. ALFWorld: Aligning Text and Embodied Environments for Interactive LearningMohit Shridhar, Xingdi Yuan, Marc-Alexandre Côté, Yonatan Bisk et al.ICLR 2021 · 819 citations
  3. Grounding Large Language Models in Interactive Environments with Online Reinforcement LearningThomas Carta, Clément Romac, Thomas Wolf, Sylvain Lamprier et al.ICML 2023 · 258 citations
  4. Take a Step Back: Evoking Reasoning via Abstraction in Large Language ModelsHuaixiu Steven Zheng, Swaroop Mishra, Xinyun Chen, Heng-Tze Cheng et al.ICLR 2024 · 216 citations
  5. Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization ApproachWeiyu Ma, Qirui Mi, Yongcheng Zeng, Xue Yan et al.NeurIPS 2024 · 122 citations

Related papers

  1. PlugMem: A Task-Agnostic Plugin Memory Module for LLM AgentsKe Yang, Zixi Chen, Xuan He, Jize Jiang et al.ICML 2026 · 20 citations
  2. Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge GraphsLiyi Chen, Panrong Tong, Zhongming Jin, Ying Sun et al.NeurIPS 2024 · 160 citations
  3. CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global MemoryWeichen Zhang, Chen Gao, Shiquan Yu, Ruiying Peng et al.ACL 2025 · 22 citations
  4. KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge GraphJinhao Jiang, Kun Zhou, Xin Zhao, Yang Song et al.ACL 2025
  5. LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term ReasoningZhengjun Huang, Zhoujin Tian, Qintian Guo, Fangyuan Zhang et al.ACL Findings 2026 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines