Saved in:
Bibliographic Details
Main Authors: Bian, Haonan, Yao, Zhiyuan, Hu, Sen, Xu, Zishan, Zhang, Shaolei, Guo, Yifu, Yang, Ziliang, Han, Xueran, Wang, Huacan, Chen, Ronghao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.06966
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • As Large Language Models (LLMs) evolve from static dialogue interfaces to autonomous general agents, effective memory is paramount to ensuring long-term consistency. However, existing benchmarks primarily focus on casual conversation or task-oriented dialogue, failing to capture **"long-term project-oriented"** interactions where agents must track evolving goals. To bridge this gap, we introduce **RealMem**, the first benchmark grounded in realistic project scenarios. RealMem comprises over 2,000 cross-session dialogues across eleven scenarios, utilizing natural user queries for evaluation. We propose a synthesis pipeline that integrates Project Foundation Construction, Multi-Agent Dialogue Generation, and Memory and Schedule Management to simulate the dynamic evolution of memory. Experiments reveal that current memory systems face significant challenges in managing the long-term project states and dynamic context dependencies inherent in real-world projects. Our code and datasets are available at [https://github.com/AvatarMemory/RealMemBench](https://github.com/AvatarMemory/RealMemBench).