Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.22320 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916764401532928 |
|---|---|
| author | Wang, Xudong Zhu, Jian Zhang, Ruichen Feng, Lei Niyato, Dusit Wang, Jiacheng Du, Hongyang Mao, Shiwen Han, Zhu |
| author_facet | Wang, Xudong Zhu, Jian Zhang, Ruichen Feng, Lei Niyato, Dusit Wang, Jiacheng Du, Hongyang Mao, Shiwen Han, Zhu |
| contents | Recent advances in large language models (LLMs) have opened new possibilities for automated reasoning and decision-making in wireless networks. However, applying LLMs to wireless communications presents challenges such as limited capability in handling complex logic, generalization, and reasoning. Chain-of-Thought (CoT) prompting, which guides LLMs to generate explicit intermediate reasoning steps, has been shown to significantly improve LLM performance on complex tasks. Inspired by this, this paper explores the application potential of CoT-enhanced LLMs in wireless communications. Specifically, we first review the fundamental theory of CoT and summarize various types of CoT. We then survey key CoT and LLM techniques relevant to wireless communication and networking. Moreover, we introduce a multi-layer intent-driven CoT framework that bridges high-level user intent expressed in natural language with concrete wireless control actions. Our proposed framework sequentially parses and clusters intent, selects appropriate CoT reasoning modules via reinforcement learning, then generates interpretable control policies for system configuration. Using the unmanned aerial vehicle (UAV) network as a case study, we demonstrate that the proposed framework significantly outperforms a non-CoT baseline in both communication performance and quality of generated reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_22320 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Chain-of-Thought for Large Language Model-empowered Wireless Communications Wang, Xudong Zhu, Jian Zhang, Ruichen Feng, Lei Niyato, Dusit Wang, Jiacheng Du, Hongyang Mao, Shiwen Han, Zhu Networking and Internet Architecture Recent advances in large language models (LLMs) have opened new possibilities for automated reasoning and decision-making in wireless networks. However, applying LLMs to wireless communications presents challenges such as limited capability in handling complex logic, generalization, and reasoning. Chain-of-Thought (CoT) prompting, which guides LLMs to generate explicit intermediate reasoning steps, has been shown to significantly improve LLM performance on complex tasks. Inspired by this, this paper explores the application potential of CoT-enhanced LLMs in wireless communications. Specifically, we first review the fundamental theory of CoT and summarize various types of CoT. We then survey key CoT and LLM techniques relevant to wireless communication and networking. Moreover, we introduce a multi-layer intent-driven CoT framework that bridges high-level user intent expressed in natural language with concrete wireless control actions. Our proposed framework sequentially parses and clusters intent, selects appropriate CoT reasoning modules via reinforcement learning, then generates interpretable control policies for system configuration. Using the unmanned aerial vehicle (UAV) network as a case study, we demonstrate that the proposed framework significantly outperforms a non-CoT baseline in both communication performance and quality of generated reasoning. |
| title | Chain-of-Thought for Large Language Model-empowered Wireless Communications |
| topic | Networking and Internet Architecture |
| url | https://arxiv.org/abs/2505.22320 |