Survey on Self-Evolving Coding Agents: Taxonomy and Challenges

NJUST1412 · hf · 2026-08-06

This paper provides a systematic survey of the emerging area of self-evolving coding agents. Although LLMs are widely deployed as coding agents to inspect repositories and debug failures, most existing systems remain static post-deployment, struggling to adapt to the dynamic nature of software development.

The authors also maintain a corresponding GitHub repository collecting relevant papers.

Original post →

More from coding & agent

coding & agent channel →