Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2601.01280 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914320127885312 |
|---|---|
| author | Hu, Sen Wei, Yuxiang Ran, Jiaxin Yao, Zhiyuan Han, Xueran Wang, Huacan Chen, Ronghao Zou, Lei |
| author_facet | Hu, Sen Wei, Yuxiang Ran, Jiaxin Yao, Zhiyuan Han, Xueran Wang, Huacan Chen, Ronghao Zou, Lei |
| contents | 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. Code are available at https://github.com/AvatarMemory/UnifiedMem |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_01280 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory Hu, Sen Wei, Yuxiang Ran, Jiaxin Yao, Zhiyuan Han, Xueran Wang, Huacan Chen, Ronghao Zou, Lei Computation and Language Artificial Intelligence 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. Code are available at https://github.com/AvatarMemory/UnifiedMem |
| title | Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.01280 |