AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917989303975936 |
|---|---|
| author | Liu, Jiahao Gu, Shengkang Li, Dongsheng Zhang, Guangping Han, Mingzhe Gu, Hansu Zhang, Peng Lu, Tun Shang, Li Gu, Ning |
| author_facet | Liu, Jiahao Gu, Shengkang Li, Dongsheng Zhang, Guangping Han, Mingzhe Gu, Hansu Zhang, Peng Lu, Tun Shang, Li Gu, Ning |
| contents | LLM-based user agents, which simulate user interaction behavior, are emerging as a promising approach to enhancing recommender systems. In real-world scenarios, users' interactions often exhibit cross-domain characteristics and are influenced by others. However, the memory design in current methods causes user agents to introduce significant irrelevant information during decision-making in cross-domain scenarios and makes them unable to recognize the influence of other users' interactions, such as popularity factors. To tackle this issue, we propose a dual-layer memory architecture combined with a two-step fusion mechanism. This design avoids irrelevant information during decision-making while ensuring effective integration of cross-domain preferences. We also introduce the concepts of interest groups and group-shared memory to better capture the influence of popularity factors on users with similar interests. Comprehensive experiments validate the effectiveness of AgentCF++. Our code is available at https://github.com/jhliu0807/AgentCF-plus. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_13843 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendations Liu, Jiahao Gu, Shengkang Li, Dongsheng Zhang, Guangping Han, Mingzhe Gu, Hansu Zhang, Peng Lu, Tun Shang, Li Gu, Ning Information Retrieval Artificial Intelligence LLM-based user agents, which simulate user interaction behavior, are emerging as a promising approach to enhancing recommender systems. In real-world scenarios, users' interactions often exhibit cross-domain characteristics and are influenced by others. However, the memory design in current methods causes user agents to introduce significant irrelevant information during decision-making in cross-domain scenarios and makes them unable to recognize the influence of other users' interactions, such as popularity factors. To tackle this issue, we propose a dual-layer memory architecture combined with a two-step fusion mechanism. This design avoids irrelevant information during decision-making while ensuring effective integration of cross-domain preferences. We also introduce the concepts of interest groups and group-shared memory to better capture the influence of popularity factors on users with similar interests. Comprehensive experiments validate the effectiveness of AgentCF++. Our code is available at https://github.com/jhliu0807/AgentCF-plus. |
| title | AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendations |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2502.13843 |