Score: 0

Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory

Published: January 3, 2026 | arXiv ID: 2601.01280v1

By: Sen Hu , Yuxiang Wei , Jiaxin Ran and more

Potential Business Impact:

Makes chatbots remember conversations better.

Business Areas:
Database Data and Analytics, Software

Graph structures are increasingly used in dialog memory systems, but empirical findings on their effectiveness remain inconsistent, making it unclear which design choices truly matter. We present an experimental, system-oriented analysis of long-term dialog memory architectures. We introduce a unified framework that decomposes dialog memory systems into core components and supports both graph-based and non-graph approaches. Under this framework, we conduct controlled, stage-wise experiments on LongMemEval and HaluMem, comparing common design choices in memory representation, organization, maintenance, and retrieval. Our results show that many performance differences are driven by foundational system settings rather than specific architectural innovations. Based on these findings, we identify stable and reliable strong baselines for future dialog memory research.

Country of Origin
🇨🇳 China

Page Count
13 pages

Category
Computer Science:
Computation and Language