Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/29476
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jiang, F | - |
dc.contributor.author | Dong, L | - |
dc.contributor.author | Peng, Y | - |
dc.contributor.author | Wang, K | - |
dc.contributor.author | Yang, K | - |
dc.contributor.author | Pan, C | - |
dc.contributor.author | Niyato, D | - |
dc.contributor.author | Dobre, OA | - |
dc.date.accessioned | 2024-08-01T18:43:25Z | - |
dc.date.available | 2024-08-01T18:43:25Z | - |
dc.date.issued | 2023-12-13 | - |
dc.identifier | ORCiD: Kezhi Wang https://orcid.org/0000-0001-8602-0800 | - |
dc.identifier | arXiv:2312.07850v1 [cs.AI] | - |
dc.identifier.citation | Jiang, F. et al. (2023) 'Large Language Model Enhanced Multi-Agent Systems for 6G Communications', arXiv:2312.07850 [cs.AI] (preprint), pp. 1 - 8. doi: 10.48550/arXiv.2312.07850. | en_US |
dc.identifier.uri | https://bura.brunel.ac.uk/handle/2438/29476 | - |
dc.description | This is an arXiv preprint. It has not been certified by peer review. | en_US |
dc.description.abstract | The rapid development of the Large Language Model (LLM) presents huge opportunities for 6G communications, e.g., network optimization and management by allowing users to input task requirements to LLMs by nature language. However, directly applying native LLMs in 6G encounters various challenges, such as a lack of private communication data and knowledge, limited logical reasoning, evaluation, and refinement abilities. Integrating LLMs with the capabilities of retrieval, planning, memory, evaluation and reflection in agents can greatly enhance the potential of LLMs for 6G communications. To this end, we propose a multi-agent system with customized communication knowledge and tools for solving communication related tasks using natural language, comprising three components: (1) Multi-agent Data Retrieval (MDR), which employs the condensate and inference agents to refine and summarize communication knowledge from the knowledge base, expanding the knowledge boundaries of LLMs in 6G communications; (2) Multi-agent Collaborative Planning (MCP), which utilizes multiple planning agents to generate feasible solutions for the communication related task from different perspectives based on the retrieved knowledge; (3) Multi-agent Evaluation and Reflecxion (MER), which utilizes the evaluation agent to assess the solutions, and applies the reflexion agent and refinement agent to provide improvement suggestions for current solutions. Finally, we validate the effectiveness of the proposed multi-agent system by designing a semantic communication system, as a case study of 6G communications. | en_US |
dc.format.extent | 1 - 8 | - |
dc.language.iso | en_US | en_US |
dc.publisher | Cornell University | en_US |
dc.rights | Copyright © 2023 The Author(s). arXiv.org perpetual, non-exclusive license 1.0 (https://arxiv.org/licenses/nonexclusive-distrib/1.0/). This license gives limited rights to arXiv to distribute the article, and also limits re-use of any type from other entities or individuals. | - |
dc.rights.uri | https://arxiv.org/licenses/nonexclusive-distrib/1.0/ | - |
dc.subject | large language model | en_US |
dc.subject | multi-agent system | en_US |
dc.subject | semantic communications | - |
dc.subject | GPT | - |
dc.subject | 6G communications. | - |
dc.title | Large Language Model Enhanced Multi-Agent Systems for 6G Communications | en_US |
dc.type | Article | en_US |
dc.date.dateAccepted | 2023-12-13 | - |
dc.identifier.doi | https://doi.org/10.48550/arXiv.2312.07850 | - |
pubs.notes | Submitted for possible journal publication | - |
dc.identifier.eissn | 2331-8422 | - |
dc.rights.license | https://arxiv.org/licenses/nonexclusive-distrib/1.0/ | - |
dc.rights.holder | The Author(s) | - |
Appears in Collections: | Dept of Computer Science Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Preprint.pdf | Copyright © 2023 The Author(s). arXiv.org perpetual, non-exclusive license 1.0 (https://arxiv.org/licenses/nonexclusive-distrib/1.0/). This license gives limited rights to arXiv to distribute the article, and also limits re-use of any type from other entities or individuals. | 1.5 MB | Adobe PDF | View/Open |
Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.