arXiv:2508.12232v5 Announce Type: replace-cross Abstract: Issue-to-commit link recovery in software repositories is fundamental to software traceability and project management, yet it remains a challenging task. Prior studies show that only about 42.2% of issues on GitHub are correctly linked to their commits, highlighting the need for more effective solutions. Existing work has explored a range of ML/DL approaches, and more recently, large language models (LLMs) have been applied to this problem. However, these methods face two major limitations. First, LLMs are restricted by limited context
The rapid advancement and increased availability of large language models are enabling their application to increasingly complex and autonomous software development tasks.
This development represents concrete progress in using LLMs for automating core engineering processes, improving efficiency and reducing manual effort in software development at scale.
The ability to autonomously link software issues to commits using LLM-based agents will streamline project management and traceability, potentially shifting how software development teams operate.
- · Software Development Teams
- · GitHub
- · AI/ML Software Providers
- · Large Language Model Developers
- · Manual Software Traceability Tools
Improved efficiency in software project management and code maintenance.
Increased adoption of AI agents for automating various stages of the software development lifecycle.
A potential reduction in the demand for certain low-level software engineering tasks, leading to a shift in required skill sets.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI