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

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...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-09
Main Authors: Anokhin, Petr, Semenov, Nikita, Sorokin, Artyom, Evseev, Dmitry, Burtsev, Mikhail, Burnaev, Evgeny
Format: Article
Language:English
Subjects:
Autonomy
Decision making
Generative artificial intelligence
Knowledge representation
Large language models
Retrieval
Task complexity
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422