Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead
Rao, Hongzhou, Zhao, Yanjie, Hou, Xinyi, Wang, Shenao, Wang, Haoyu
–arXiv.org Artificial Intelligence
The rapid advancement of large language models (LLMs) has redefined artificial intelligence (AI), pushing the boundaries of AI research and enabling unbounded possibilities for both academia and the industry. However, LLM development faces increasingly complex challenges throughout its lifecycle, yet no existing research systematically explores these challenges and solutions from the perspective of software engineering (SE) approaches. To fill the gap, we systematically analyze research status throughout the LLM development lifecycle, divided into six phases: requirements engineering, dataset construction, model development and enhancement, testing and evaluation, deployment and operations, and maintenance and evolution. We then conclude by identifying the key challenges for each phase and presenting potential research directions to address these challenges. In general, we provide valuable insights from an SE perspective to facilitate future advances in LLM development.
arXiv.org Artificial Intelligence
Jul-1-2025
- Country:
- Asia
- China > Hubei Province
- Wuhan (0.04)
- Middle East > Jordan (0.04)
- Myanmar > Tanintharyi Region
- Dawei (0.04)
- China > Hubei Province
- Europe
- Italy > Calabria
- Catanzaro Province > Catanzaro (0.04)
- Portugal
- Switzerland > Basel-City
- Basel (0.04)
- Italy > Calabria
- North America > United States
- New York > New York County
- New York City (0.04)
- Virginia (0.04)
- New York > New York County
- South America > Uruguay
- Asia
- Genre:
- Overview (1.00)
- Research Report > New Finding (0.92)
- Industry:
- Education (0.67)
- Energy (1.00)
- Government (1.00)
- Health & Medicine (1.00)
- Information Technology > Security & Privacy (1.00)
- Law (1.00)
- Technology: