APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI
Pratyay Banerjee, Masud Moshtaghi, Shivashankar Subramanian, Amita Misra, Ankit Chadha
TLDR
APEX-MEM is a novel conversational memory system using a property graph and a multi-tool retrieval agent for robust long-term AI interactions.
Key contributions
- Structures conversations as temporally grounded events using a domain-agnostic property graph.
- Employs append-only storage to preserve the complete temporal evolution of information.
- Uses a multi-tool retrieval agent to resolve conflicting data and generate concise memory summaries.
Why it matters
APEX-MEM significantly improves long-term conversational AI by structuring memory with property graphs and an intelligent retrieval agent. This resolves conflicting information at query time, leading to more coherent and accurate interactions. It outperforms state-of-the-art, offering a robust solution for persistent AI memory.
Original 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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.