STMA：一個用於長時間範圍具體任務規劃的時空記憶代理程式

STMA: A Spatio-Temporal Memory Agent for Long-Horizon Embodied Task Planning

February 14, 2025

作者: Mingcong Lei, Yiming Zhao, Ge Wang, Zhixin Mai, Shuguang Cui, Yatong Han, Jinke Ren

cs.AI

摘要

具體智能的一個關鍵目標是使代理人能夠在動態環境中執行長期任務，同時保持堅固的決策能力和適應性。為了實現這一目標，我們提出了時空記憶代理人（STMA），這是一個旨在通過整合時空記憶來增強任務規劃和執行的新框架。STMA建立在三個關鍵組件之上：（1）一個捕捉實時歷史和環境變化的時空記憶模塊，（2）一個促進適應性空間推理的動態知識圖，以及（3）一個迭代地優化任務策略的規劃者-評論者機制。我們在TextWorld環境中對STMA進行了評估，涉及32個任務，包括多步規劃和在不同複雜程度下的探索。實驗結果表明，與最先進的模型相比，STMA的成功率提高了31.25％，平均分數增加了24.7％。結果突顯了時空記憶在提升具體智能代理人記憶能力方面的有效性。

English

A key objective of embodied intelligence is enabling agents to perform long-horizon tasks in dynamic environments while maintaining robust decision-making and adaptability. To achieve this goal, we propose the Spatio-Temporal Memory Agent (STMA), a novel framework designed to enhance task planning and execution by integrating spatio-temporal memory. STMA is built upon three critical components: (1) a spatio-temporal memory module that captures historical and environmental changes in real time, (2) a dynamic knowledge graph that facilitates adaptive spatial reasoning, and (3) a planner-critic mechanism that iteratively refines task strategies. We evaluate STMA in the TextWorld environment on 32 tasks, involving multi-step planning and exploration under varying levels of complexity. Experimental results demonstrate that STMA achieves a 31.25% improvement in success rate and a 24.7% increase in average score compared to the state-of-the-art model. The results highlight the effectiveness of spatio-temporal memory in advancing the memory capabilities of embodied agents.