Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917451856347136 |
|---|---|
| author | Wu, Yanchen Lin, Tenghui Zhou, Yingli Zhang, Fangyuan Guo, Qintian Zhou, Xun Wang, Sibo Liu, Xilin Ma, Yuchi Fang, Yixiang |
| author_facet | Wu, Yanchen Lin, Tenghui Zhou, Yingli Zhang, Fangyuan Guo, Qintian Zhou, Xun Wang, Sibo Liu, Xilin Ma, Yuchi Fang, Yixiang |
| contents | Memory emerges as the core module in the large language model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), where memory can enable knowledge accumulation, iterative reasoning and self-evolution. A number of memory methods have been proposed in the literature. However, these methods have not been systematically and comprehensively compared under the same experimental settings. In this paper, we first summarize a unified framework that incorporates all the existing agent memory methods from a high-level perspective. We then extensively compare representative agent memory methods on two well-known benchmarks and examine the effectiveness of all methods, providing a thorough analysis of those methods. As a byproduct of our experimental analysis, we also design a new memory method by exploiting modules in the existing methods, which outperforms the state-of-the-art methods. Finally, based on these findings, we offer promising future research opportunities. We believe that a deeper understanding of the behavior of existing methods can provide valuable new insights for future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_01707 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework Wu, Yanchen Lin, Tenghui Zhou, Yingli Zhang, Fangyuan Guo, Qintian Zhou, Xun Wang, Sibo Liu, Xilin Ma, Yuchi Fang, Yixiang Computation and Language Databases Memory emerges as the core module in the large language model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), where memory can enable knowledge accumulation, iterative reasoning and self-evolution. A number of memory methods have been proposed in the literature. However, these methods have not been systematically and comprehensively compared under the same experimental settings. In this paper, we first summarize a unified framework that incorporates all the existing agent memory methods from a high-level perspective. We then extensively compare representative agent memory methods on two well-known benchmarks and examine the effectiveness of all methods, providing a thorough analysis of those methods. As a byproduct of our experimental analysis, we also design a new memory method by exploiting modules in the existing methods, which outperforms the state-of-the-art methods. Finally, based on these findings, we offer promising future research opportunities. We believe that a deeper understanding of the behavior of existing methods can provide valuable new insights for future research. |
| title | Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework |
| topic | Computation and Language Databases |
| url | https://arxiv.org/abs/2604.01707 |