AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents
This addresses the challenge of enabling autonomous agents to reason and plan effectively in new environments, though it appears incremental as it builds on existing memory and knowledge graph techniques.
The paper tackles the problem of unstructured memory representations in LLM-based agents by introducing AriGraph, a method that constructs and updates a memory graph integrating semantic and episodic memories, resulting in marked outperformance over established memory methods and strong RL baselines in complex interactive text game environments.
Advancements in the capabilities of Large Language Models (LLMs) have created a promising foundation for developing autonomous agents. With the right tools, these agents could learn to solve tasks in new environments by accumulating and updating their knowledge. Current LLM-based agents process past experiences using a full history of observations, summarization, 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 and updates a memory graph that integrates semantic and episodic memories while exploring the environment. We demonstrate that our Ariadne LLM agent, consisting of the proposed memory architecture augmented with planning and decision-making, effectively handles complex tasks within interactive text game environments difficult even for human players. Results show that our approach markedly outperforms other established memory methods and strong RL baselines in a range of problems of varying complexity. Additionally, AriGraph demonstrates competitive performance compared to dedicated knowledge graph-based methods in static multi-hop question-answering.