When Large Language Model Agents Meet 6G Networks: Perception, Grounding, and Alignment
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929246354538496 |
|---|---|
| author | Xu, Minrui Niyato, Dusit Kang, Jiawen Xiong, Zehui Mao, Shiwen Han, Zhu Kim, Dong In Letaief, Khaled B. |
| author_facet | Xu, Minrui Niyato, Dusit Kang, Jiawen Xiong, Zehui Mao, Shiwen Han, Zhu Kim, Dong In Letaief, Khaled B. |
| contents | AI agents based on multimodal large language models (LLMs) are expected to revolutionize human-computer interaction and offer more personalized assistant services across various domains like healthcare, education, manufacturing, and entertainment. Deploying LLM agents in 6G networks enables users to access previously expensive AI assistant services via mobile devices democratically, thereby reducing interaction latency and better preserving user privacy. Nevertheless, the limited capacity of mobile devices constrains the effectiveness of deploying and executing local LLMs, which necessitates offloading complex tasks to global LLMs running on edge servers during long-horizon interactions. In this article, we propose a split learning system for LLM agents in 6G networks leveraging the collaboration between mobile devices and edge servers, where multiple LLMs with different roles are distributed across mobile devices and edge servers to perform user-agent interactive tasks collaboratively. In the proposed system, LLM agents are split into perception, grounding, and alignment modules, facilitating inter-module communications to meet extended user requirements on 6G network functions, including integrated sensing and communication, digital twins, and task-oriented communications. Furthermore, we introduce a novel model caching algorithm for LLMs within the proposed system to improve model utilization in context, thus reducing network costs of the collaborative mobile and edge LLM agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_07764 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | When Large Language Model Agents Meet 6G Networks: Perception, Grounding, and Alignment Xu, Minrui Niyato, Dusit Kang, Jiawen Xiong, Zehui Mao, Shiwen Han, Zhu Kim, Dong In Letaief, Khaled B. Artificial Intelligence Networking and Internet Architecture AI agents based on multimodal large language models (LLMs) are expected to revolutionize human-computer interaction and offer more personalized assistant services across various domains like healthcare, education, manufacturing, and entertainment. Deploying LLM agents in 6G networks enables users to access previously expensive AI assistant services via mobile devices democratically, thereby reducing interaction latency and better preserving user privacy. Nevertheless, the limited capacity of mobile devices constrains the effectiveness of deploying and executing local LLMs, which necessitates offloading complex tasks to global LLMs running on edge servers during long-horizon interactions. In this article, we propose a split learning system for LLM agents in 6G networks leveraging the collaboration between mobile devices and edge servers, where multiple LLMs with different roles are distributed across mobile devices and edge servers to perform user-agent interactive tasks collaboratively. In the proposed system, LLM agents are split into perception, grounding, and alignment modules, facilitating inter-module communications to meet extended user requirements on 6G network functions, including integrated sensing and communication, digital twins, and task-oriented communications. Furthermore, we introduce a novel model caching algorithm for LLMs within the proposed system to improve model utilization in context, thus reducing network costs of the collaborative mobile and edge LLM agents. |
| title | When Large Language Model Agents Meet 6G Networks: Perception, Grounding, and Alignment |
| topic | Artificial Intelligence Networking and Internet Architecture |
| url | https://arxiv.org/abs/2401.07764 |