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

2024/07/05 by Petr Anokhin, Anokhin, Petr, Nikita Semenov +10 · 16 citations
Computer Science · Decision Sciences · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Data Quality and Management #FOS: Computer and information sciences #Semantic Web and Ontologies

paper · pdf · doi:10.48550/arxiv.2407.04363

openalex publication_date 2024/07/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory
• Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models
• Reuse, Don't Recompute: Efficient Large Reasoning Model Inference via Memory Orchestration
• ENGRAM: Effective, Lightweight Memory Orchestration for Conversational Agents
• Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training
• RGMem: Renormalization Group-inspired Memory Evolution for Language Agents
• ATOM: AdapTive and OptiMized dynamic temporal knowledge graph construction using LLMs
• Multi-dimensional Data Analysis and Applications Basing on LLM Agents and Knowledge Graph Interactions
• Revealing Interconnections between Diseases: from Statistical Methods to Large Language Models
• Mem-α: Learning Memory Construction via Reinforcement Learning
• Beyond Manuals and Tasks: Instance-Level Context Learning for LLM Agents
• LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions
• Memory in Large Language Models: Mechanisms, Evaluation and Evolution
• M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environments
• ZhiFangDanTai: Fine-tuning Graph-based Retrieval-Augmented Generation Model for Traditional Chinese Medicine Formula
• Nemori: Self-Organizing Agent Memory Inspired by Cognitive Science

Related

• PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM agents
• From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory
• A-MEM: Agentic Memory for LLM Agents
• Taming the Untamed: Graph-Based Knowledge Retrieval and Reasoning for MLLMs to Conquer the Unknown
• KG-RAG: Bridging the Gap Between Knowledge and Creativity