LLM Agent for Hyper-Parameter Optimization
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913933092192256 |
|---|---|
| author | Wang, Wanzhe Peng, Jianqiu Hu, Menghao Zhong, Weihuang Zhang, Tong Wang, Shuai Zhang, Yixin Shao, Mingjie Ni, Wanli |
| author_facet | Wang, Wanzhe Peng, Jianqiu Hu, Menghao Zhong, Weihuang Zhang, Tong Wang, Shuai Zhang, Yixin Shao, Mingjie Ni, Wanli |
| contents | Hyper-parameters are essential and critical for the performance of communication algorithms. However, current hyper-parameters optimization approaches for Warm-Start Particles Swarm Optimization with Crossover and Mutation (WS-PSO-CM) algorithm, designed for radio map-enabled unmanned aerial vehicle (UAV) trajectory and communication, are primarily heuristic-based, exhibiting low levels of automation and improvable performance. In this paper, we design an Large Language Model (LLM) agent for automatic hyper-parameters-tuning, where an iterative framework and Model Context Protocol (MCP) are applied. In particular, the LLM agent is first set up via a profile, which specifies the boundary of hyper-parameters, task objective, terminal condition, conservative or aggressive strategy of optimizing hyper-parameters, and LLM configurations. Then, the LLM agent iteratively invokes WS-PSO-CM algorithm for exploration. Finally, the LLM agent exits the loop based on the terminal condition and returns an optimized set of hyperparameters. Our experiment results show that the minimal sum-rate achieved by hyper-parameters generated via our LLM agent is significantly higher than those by both human heuristics and random generation methods. This indicates that an LLM agent with PSO and WS-PSO-CM algorithm knowledge is useful in seeking high-performance hyper-parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_15167 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM Agent for Hyper-Parameter Optimization Wang, Wanzhe Peng, Jianqiu Hu, Menghao Zhong, Weihuang Zhang, Tong Wang, Shuai Zhang, Yixin Shao, Mingjie Ni, Wanli Information Theory Artificial Intelligence Hyper-parameters are essential and critical for the performance of communication algorithms. However, current hyper-parameters optimization approaches for Warm-Start Particles Swarm Optimization with Crossover and Mutation (WS-PSO-CM) algorithm, designed for radio map-enabled unmanned aerial vehicle (UAV) trajectory and communication, are primarily heuristic-based, exhibiting low levels of automation and improvable performance. In this paper, we design an Large Language Model (LLM) agent for automatic hyper-parameters-tuning, where an iterative framework and Model Context Protocol (MCP) are applied. In particular, the LLM agent is first set up via a profile, which specifies the boundary of hyper-parameters, task objective, terminal condition, conservative or aggressive strategy of optimizing hyper-parameters, and LLM configurations. Then, the LLM agent iteratively invokes WS-PSO-CM algorithm for exploration. Finally, the LLM agent exits the loop based on the terminal condition and returns an optimized set of hyperparameters. Our experiment results show that the minimal sum-rate achieved by hyper-parameters generated via our LLM agent is significantly higher than those by both human heuristics and random generation methods. This indicates that an LLM agent with PSO and WS-PSO-CM algorithm knowledge is useful in seeking high-performance hyper-parameters. |
| title | LLM Agent for Hyper-Parameter Optimization |
| topic | Information Theory Artificial Intelligence |
| url | https://arxiv.org/abs/2506.15167 |