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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Banerjee, Pratyay, Moshtaghi, Masud, Subramanian, Shivashankar, Misra, Amita, Chadha, Ankit
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917411835346944
author Banerjee, Pratyay
Moshtaghi, Masud
Subramanian, Shivashankar
Misra, Amita
Chadha, Ankit
author_facet Banerjee, Pratyay
Moshtaghi, Masud
Subramanian, Shivashankar
Misra, Amita
Chadha, Ankit
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_14362
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI
Banerjee, Pratyay
Moshtaghi, Masud
Subramanian, Shivashankar
Misra, Amita
Chadha, Ankit
Computation and Language
Artificial Intelligence
Information Retrieval
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.
title APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2604.14362