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

arXiv: https://arxiv.org/abs/2604.14362 · HTML: https://mlsanity.com/paper/2604.14362/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 15 Apr 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 16 of 16)

- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [MIRIX: Multi-Agent Memory System for LLM-Based Agents](https://mlsanity.com/paper/2507.07957/) (2025)
- [A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts](https://mlsanity.com/paper/2402.09727/) (2024)
- [Context Length Alone Hurts LLM Performance Despite Perfect Retrieval](https://mlsanity.com/paper/2510.05381/) (2025)
- [MemInsight: Autonomous Memory Augmentation for LLM Agents](https://mlsanity.com/paper/2503.21760/) (2025)
- [SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models](https://mlsanity.com/paper/2506.01062/) (2025)
- [Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents](https://mlsanity.com/paper/2507.22925/) (2025)
- [What Deserves Memory: Adaptive Memory Distillation for LLM Agents](https://mlsanity.com/paper/2508.03341/) (2025)
- [Toward Conversational Agents with Context and Time Sensitive Long-term Memory](https://mlsanity.com/paper/2406.00057/) (2024)
- [Self-Consistency Falls Short! The Adverse Effects of Positional Bias on Long-Context Problems](https://mlsanity.com/paper/2411.01101/) (2024)
- [Semantic Anchoring in Agentic Memory: Leveraging Linguistic Structures for Persistent Conversational Context](https://mlsanity.com/paper/2508.12630/) (2025)

## Built on by (most cited first, 17 of 17)

- [TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memory](https://mlsanity.com/paper/2606.06240/) (2026)
- [Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMs](https://mlsanity.com/paper/2609.10413/) (2026)
- [Compute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV](https://mlsanity.com/paper/2607.23693/) (2026)
- [VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction](https://mlsanity.com/paper/2608.26005/) (2026)
- [When Stories Evolve: Benchmarking LLM Storytelling Across Agent Architectures in Open-Ended World Simulations](https://mlsanity.com/paper/2608.15654/) (2026)
- [CABLE: Extending the Reach of Memory Retrieval via Complementary Antecedent-Based Linking and Expansion](https://mlsanity.com/paper/2608.17911/) (2026)
- [JustMem: Just-Enough Memory Access for Long-Term Conversations](https://mlsanity.com/paper/2609.19877/) (2026)
- [Memory Control Signals Emerge Before Action in Long Horizon Agents](https://mlsanity.com/paper/2609.27286/) (2026)
- [Governed Persistent Memory: Source-Bound State Semantics and Fail-Closed Release for Long-Horizon Agents](https://mlsanity.com/paper/2608.12476/) (2026)
- [Entity-Memory Graph Retrieval Improves Evidence Coverage in Long-Conversation Question Answering](https://mlsanity.com/paper/2608.27925/) (2026)
- [Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and Evaluation](https://mlsanity.com/paper/2609.08599/) (2026)
- [ROAM: Robust Organization of Atomic Memories for Agents through Semantic Relations](https://mlsanity.com/paper/2609.09778/) (2026)
- [Propose, Verify, Commit: Evidence-Grounded Memory for Long-Horizon Multi-Actor Conversations](https://mlsanity.com/paper/2609.23465/) (2026)
- [Contract Memory Compiler: Resolve, Then Traverse](https://mlsanity.com/paper/2609.32658/) (2026)
- [Personalized State-Transition-Aware Memory for Clinical Agents](https://mlsanity.com/paper/2609.38490/) (2026)
- [CAVE-Mem: Boundary-Aware Experience Validation for Memory Search](https://mlsanity.com/paper/2610.00238/) (2026)
- [Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational Agents](https://mlsanity.com/paper/2610.11920/) (2026)

## Abstract (arXiv)

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.