Automatically Improving The Code Quality Of Rust Via LLM

In this thesis, the research objective is to define and resolve the challenges of leveraging LLM to automatically improve Rust’s code quality. The application of LLMs to Rust code quality improvement requires addressing fundamental challenges in three key areas: generating compilable code that satisfies Rust’s strict type system, detecting subtle safety violations that escape traditional analysis, and creating comprehensive test suites that achieve meaningful code coverage. These challenges necessitate novel approaches that combine LLMs with program analysis techniques specifically designed for Rust’s unique characteristics.

Level thesis:degree_level

Doctoral

Department dc:contributor.department

Computer Science

Grantor dc:publisher

Georgia Institute of Technology

Year dc:date.issued

2025

Author dc:creator

• Cheng, Xiang

Advisor dc:contributor.advisor

• Kim, Taesoo

Committee members dc:contributor.committeemember

• Orso, Alessandro
• Zhang, Qirun
• Zhang, Xiaokuan
• Saltaformaggio, Brendan

• Rust
• LLM

Language dc:language.iso

en_US

Handle dc:identifier.uri

https://hdl.handle.net/1853/78728

OAI identifier oai:identifier

oai:repository.gatech.edu:1853/78728