APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI

TL;DR

APEX-MEM introduces a structured, temporal, and entity-centric memory system for long-term conversational AI, improving coherence and accuracy over existing methods.

Contribution

It combines a property graph, append-only storage, and a multi-tool retrieval agent to enhance long-term memory in conversational models.

Findings

Achieves 88.88% accuracy on LOCOMO QA task.

Achieves 86.2% accuracy on LongMemEval.

Outperforms state-of-the-art session-aware approaches.

Abstract

Large language models still struggle with reliable long-term conversational memory: simply enlarging context windows or applying naive retrieval often introduces noise and destabilizes responses. We present APEX-MEM, a conversational memory system that combines three key innovations: (1) a property graph which uses domain-agnostic ontology to structure conversations as temporally grounded events in an entity-centric framework, (2) append-only storage that preserves the full temporal evolution of information, and (3) a multi-tool retrieval agent that understands and resolves conflicting or evolving information at query time, producing a compact and contextually relevant memory summary. This retrieval-time resolution preserves the full interaction history while suppressing irrelevant details. APEX-MEM achieves 88.88% accuracy on LOCOMO's Question Answering task and 86.2% on LongMemEval, outperforming state-of-the-art session-aware approaches and demonstrating that structured property graphs enable more temporally coherent long-term conversational reasoning.