AriGraph：使用情節記憶學習知識圖世界模型以提升LLM智能體

AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents

July 5, 2024

作者: Petr Anokhin, Nikita Semenov, Artyom Sorokin, Dmitry Evseev, Mikhail Burtsev, Evgeny Burnaev

cs.AI

摘要

生成式人工智慧的進步擴展了大型語言模型（LLMs）在自主代理開發中的潛在應用。實現真正的自主性需要積累並更新從與環境互動中獲得的知識，並有效利用它。目前基於LLM的方法利用過去的經驗，使用完整的觀察歷史、摘要或檢索增強。然而，這些非結構化記憶表示並不促進複雜決策所需的推理和規劃。在我們的研究中，我們介紹了AriGraph，一種新穎的方法，其中代理構建一個記憶圖，整合語義和情節記憶，同時探索環境。這種圖結構有助於有效地聯想檢索相互關聯的概念，與代理的當前狀態和目標相關，因此作為一個有效的環境模型，增強了代理的探索和規劃能力。我們展示了我們的Ariadne LLM代理，配備了這種提出的記憶架構，增強了規劃和決策，能夠在TextWorld環境中以零樣本基礎有效處理複雜任務。我們的方法在各種任務中明顯優於已建立的方法，如完整歷史、摘要和檢索增強生成，包括第一屆TextWorld Problems競賽中的烹飪挑戰以及新任務，如清潔房屋和解謎尋寶。

English

Advancements in generative AI have broadened the potential applications of Large Language Models (LLMs) in the development of autonomous agents. Achieving true autonomy requires accumulating and updating knowledge gained from interactions with the environment and effectively utilizing it. Current LLM-based approaches leverage past experiences using a full history of observations, summarization or retrieval augmentation. However, these unstructured memory representations do not facilitate the reasoning and planning essential for complex decision-making. In our study, we introduce AriGraph, a novel method wherein the agent constructs a memory graph that integrates semantic and episodic memories while exploring the environment. This graph structure facilitates efficient associative retrieval of interconnected concepts, relevant to the agent's current state and goals, thus serving as an effective environmental model that enhances the agent's exploratory and planning capabilities. We demonstrate that our Ariadne LLM agent, equipped with this proposed memory architecture augmented with planning and decision-making, effectively handles complex tasks on a zero-shot basis in the TextWorld environment. Our approach markedly outperforms established methods such as full-history, summarization, and Retrieval-Augmented Generation in various tasks, including the cooking challenge from the First TextWorld Problems competition and novel tasks like house cleaning and puzzle Treasure Hunting.