MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents
This work addresses the problem of persistent memory in LLMs for long-term personalized conversations, a key limitation for conversational AI agents.
MemORAI introduces a graph-based memory framework for LLMs that uses selective filtering, provenance tracking, and query-adaptive retrieval, achieving state-of-the-art performance on LOCOMO and LongMemEval benchmarks for personalized conversational agents.
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.