# LifeBench: A Benchmark for Long-Horizon Multi-Source Memory

arXiv: https://arxiv.org/abs/2603.03781 · HTML: https://mlsanity.com/paper/2603.03781/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 47 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 13 of 13)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (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)
- [Beyond Goldfish Memory: Long-Term Open-Domain Conversation](https://mlsanity.com/paper/2107.07567/) (2021)
- [MIRIX: Multi-Agent Memory System for LLM-Based Agents](https://mlsanity.com/paper/2507.07957/) (2025)
- [MemInsight: Autonomous Memory Augmentation for LLM Agents](https://mlsanity.com/paper/2503.21760/) (2025)
- [Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs](https://mlsanity.com/paper/2310.02619/) (2023)
- [TrajLLM: A Modular LLM-Enhanced Agent-Based Framework for Realistic Human Trajectory Simulation](https://mlsanity.com/paper/2502.18712/) (2025)
- [Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction](https://mlsanity.com/paper/2511.13410/) (2025)
- [TimelineQA: A Benchmark for Question Answering over Timelines](https://mlsanity.com/paper/2306.01069/) (2023)
- [AppGen: Mobility-aware App Usage Behavior Generation for Mobile Users](https://mlsanity.com/paper/2412.07267/) (2024)

## Built on by (most cited first, 10 of 10)

- [LLMs Corrupt Your Documents When You Delegate](https://mlsanity.com/paper/2604.15597/) (2026)
- [LUNAR: Benchmarking Personalized Large Language Models on UNiversal User BehAvioR Logs](https://mlsanity.com/paper/2608.05246/) (2026)
- [Opal: Private Memory for Personal AI](https://mlsanity.com/paper/2604.02522/) (2026)
- [Synthetic Computers at Scale for Long-Horizon Productivity Simulation](https://mlsanity.com/paper/2604.28181/) (2026)
- [Selective QA over Conflicting Multi-Source Personal Memory: A Diagnostic Testbed and Method Comparison](https://mlsanity.com/paper/2605.30087/) (2026)
- [Memory Has Geometry: Non-Uniform Geometric Memory for Long-Horizon Personalized AI](https://mlsanity.com/paper/2609.17969/) (2026)
- [Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue](https://mlsanity.com/paper/2606.01223/) (2026)
- [Know It, Act on It: Investigating Memory Utilization in LLM Personalization](https://mlsanity.com/paper/2607.29433/) (2026)
- [MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale](https://mlsanity.com/paper/2608.02613/) (2026)
- [MemFuse: Multi-Source Memory Fusion from Fragmented Observations](https://mlsanity.com/paper/2608.18704/) (2026)

## Abstract (arXiv)

Long-term memory is fundamental for personalized agents capable of accumulating knowledge, reasoning over user experiences, and adapting across time. However, existing memory benchmarks primarily target declarative memory, specifically semantic and episodic types, where all information is explicitly presented in dialogues. In contrast, real-world actions are also governed by non-declarative memory, including habitual and procedural types, and need to be inferred from diverse digital traces. To bridge this gap, we introduce Lifebench, which features densely connected, long-horizon event simulation. It pushes AI agents beyond simple recall, requiring the integration of declarative and non-declarative memory reasoning across diverse and temporally extended contexts. Building such a benchmark presents two key challenges: ensuring data quality and scalability. We maintain data quality by employing real-world priors, including anonymized social surveys, map APIs, and holiday-integrated calendars, thus enforcing fidelity, diversity and behavioral rationality within the dataset. Towards scalability, we draw inspiration from cognitive science and structure events according to their partonomic hierarchy; enabling efficient parallel generation while maintaining global coherence. Performance results show that top-tier, state-of-the-art memory systems reach just 55.2% accuracy, highlighting the inherent difficulty of long-horizon retrieval and multi-source integration within our proposed benchmark. The dataset and data synthesis code are available at https://github.com/1754955896/LifeBench.