AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities

TL;DR

This survey reviews the emerging field of AI agentic programming, focusing on LLM-based coding agents that autonomously plan, execute, and interact with development tools, reshaping software creation practices.

Contribution

It introduces a taxonomy of agent behaviors and system architectures, and discusses techniques, challenges, and future opportunities in AI agentic programming.

Findings

Provides a comprehensive taxonomy of agent behaviors

Examines techniques for planning and tool integration

Highlights challenges and future research directions

Abstract

AI agentic programming is an emerging paradigm where large language model (LLM)-based coding agents autonomously plan, execute, and interact with tools such as compilers, debuggers, and version control systems. Unlike conventional code generation, these agents decompose goals, coordinate multi-step processes, and adapt based on feedback, reshaping software development practices. This survey provides a timely review of the field, introducing a taxonomy of agent behaviors and system architectures and examining relevant techniques for planning, context management, tool integration, execution monitoring, and benchmarking datasets. We highlight challenges of this fast-moving field and discuss opportunities for building reliable, transparent, and collaborative coding agents.