# DynamicMem: A Long-Horizon Memory Benchmark in Real-World Settings

arXiv: https://arxiv.org/abs/2606.22877 · HTML: https://mlsanity.com/paper/2606.22877/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 30 of its 44 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 30 of 30)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [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)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [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)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions](https://mlsanity.com/paper/2507.05257/) (2025)
- [MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent](https://mlsanity.com/paper/2507.02259/) (2025)
- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025)
- [From RAG to Memory: Non-Parametric Continual Learning for Large Language Models](https://mlsanity.com/paper/2502.14802/) (2025)
- [Augmenting Language Models with Long-Term Memory](https://mlsanity.com/paper/2306.07174/) (2023)
- [Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale](https://mlsanity.com/paper/2504.14225/) (2025)
- [SimpleMem: Efficient Lifelong Memory for LLM Agents](https://mlsanity.com/paper/2601.02553/) (2026)
- [In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents](https://mlsanity.com/paper/2503.08026/) (2025)
- [MEMORYLLM: Towards Self-Updatable Large Language Models](https://mlsanity.com/paper/2402.04624/) (2024)
- [PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory](https://mlsanity.com/paper/2512.06688/) (2025)
- [MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents](https://mlsanity.com/paper/2506.21605/) (2025)
- [Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents](https://mlsanity.com/paper/2601.01885/) (2026)
- [M+: Extending MemoryLLM with Scalable Long-Term Memory](https://mlsanity.com/paper/2502.00592/) (2025)
- [SimUSER: Simulating User Behavior with Large Language Models for Recommender System Evaluation](https://mlsanity.com/paper/2504.12722/) (2025)
- [O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents](https://mlsanity.com/paper/2511.13593/) (2025)
- [PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Process](https://mlsanity.com/paper/2507.04607/) (2025)
- [Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction](https://mlsanity.com/paper/2511.13410/) (2025)
- [KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions](https://mlsanity.com/paper/2601.04745/) (2026)
- [TimelineQA: A Benchmark for Question Answering over Timelines](https://mlsanity.com/paper/2306.01069/) (2023)
- [Convomem Benchmark: Why Your First 150 Conversations Don't Need RAG](https://mlsanity.com/paper/2511.10523/) (2025)
- [CloneMem: Benchmarking Long-Term Memory for AI Clones](https://mlsanity.com/paper/2601.07023/) (2026)
- [MemGym: a Long-Horizon Memory Environment for LLM Agents](https://mlsanity.com/paper/2605.20833/) (2026)

## Built on by (most cited first, 4 of 4)

- [A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory](https://mlsanity.com/paper/2607.01935/) (2026)
- [LUNAR: Benchmarking Personalized Large Language Models on UNiversal User BehAvioR Logs](https://mlsanity.com/paper/2608.05246/) (2026)
- [Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent](https://mlsanity.com/paper/2609.38604/) (2026)
- [When Context Changes: Understanding Update Failures in LLMs](https://mlsanity.com/paper/2609.38866/) (2026)

## Abstract (arXiv)

LLM agents increasingly act as personal assistants that must remember a user's profile over months: who they are (attributes), what they routinely do (habits), and what they prefer (preferences), and keep it updated as jobs, routines, and tastes drift. Existing benchmarks evaluate this "memory" ability through short, simplified interactions, missing three core properties of real behavior: the profile is heterogeneous, with attributes, habits, and preferences evolving on different timelines; changes are driven by external context such as seasons and life events; and evidence is rarely stated explicitly, instead scattered across many small actions in different apps that a memory system must infer from. We introduce DynamicMem, a synthetic benchmark that constructs 15 months of activity per user, providing long-term multi-app data that real users' privacy keeps out of reach. It provides user-consistent trajectories averaging 2.2M tokens and 1,772 grounded events per user across 16 applications such as e-commerce, fitness, and social platforms. The profile evolves over this period and is never given explicitly: each attribute, habit, or preference must be inferred from small signals scattered across apps. We evaluate at five quarterly checkpoints to track how systems scale as history grows. Benchmarking five representative systems exposes problems a single accuracy score hides: (i) profile reconstruction degrades with history length while service-task accuracy stays flat, despite both drawing on the same memory; (ii) no system both keeps facts that stay true and replaces facts that change, with errors clustering on preferences and on naming the exact referent; and (iii) over 93% of failures trace to what the memory retrieves, not to the model writing the answer, so the largest room for improvement lies in memory itself. Code: https://wenyaxie023.github.io/DynamicMem/