MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents

TL;DR

MemORAI is a novel framework that enhances LLM conversational agents by integrating selective memory filtering, provenance tracking, and adaptive subgraph retrieval, leading to improved personalized responses.

Contribution

The paper introduces MemORAI, a new memory system combining selective filtering, provenance-enriched graphs, and query-adaptive retrieval for better LLM conversations.

Findings

Achieves state-of-the-art results on LOCOMO and LongMemEval benchmarks.

Improves memory retrieval accuracy and personalized response quality.

Demonstrates the importance of adaptive retrieval and provenance in LLM memory systems.

Abstract

Large Language Models (LLMs) lack persistent memory for long-term personalized conversations. Existing graph-based memory systems suffer from information dilution, absent provenance tracking, and uniform retrieval that ignores query context. We introduce MemORAI (Memory Organization and Retrieval via Adaptive Graph Intelligence), a framework that integrates three innovations: selective memory filtering with dual-layer compression to retain user-persona-relevant content, a provenance-enriched multi-relational graph tracking factual origins at the turn level, and query-adaptive subgraph retrieval with Dynamic Weighted PageRank that applies query-conditioned edge weighting. Evaluated on LOCOMO and LongMemEval benchmarks, MemORAI achieves state-of-the-art performance in memory retrieval and personalized response generation, demonstrating that selective storage, enriched representation, and adaptive retrieval are essential for coherent, personalized LLM agents.