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.
- Definition & Taxonomy: The paper distinguishes self-evolving coding agents from conventional ones and proposes an object-centered taxonomy characterizing what evolves (e.g., framework, memory, skills, tools, models).
- Evolutionary Dimensions: It complements this taxonomy with two orthogonal perspectives: when evolution occurs and what software-specific evidence drives it.
- Challenges & Opportunities: It highlights that executable feedback and repository context make software engineering a natural domain for agent self-evolution. However, this also introduces new challenges in feedback reliability, benchmark overfitting, safety, maintainability, cost, and generalization.
The authors also maintain a corresponding GitHub repository collecting relevant papers.
More from coding & agent
- Ending AI Slop: Engineering Fuzzy Tasks into Clear Ground Truths — _ScottCondron · 2026-08-06
- AWS Bedrock Launches Native Web Search for OpenAI Models — DigitalColmer · 2026-08-06
- Dev Uses Claude Opus to Write C Code Driving ESP32 S3 Hardware — petewoodbridge · 2026-08-06
- Beyond Generated Video: Using Agents to Automate Product Demo Shoots — socialwithaayan · 2026-08-06
- Paper Proposes Token-Native Storage Architecture for AI Agents — bclavie · 2026-08-06
- What STT do you use for production voice agents? Devs say LLM often blamed, but issues lie in voice pipeline — potqtocake · 2026-08-06