CODESTRUCT: Code Agents over Structured Action Spaces

📰 ArXiv cs.AI

CODESTRUCT reframes codebases as structured action spaces for LLM-based code agents to operate on named AST entities

advanced Published 8 Apr 2026
Action Steps
  1. Reframe codebases as structured action spaces
  2. Operate on named AST entities rather than text spans
  3. Use readCode to retrieve complete syntactic units
  4. Apply syntax-validated transformations with editCode
Who Needs to Know This

Software engineers and AI researchers on a team benefit from CODESTRUCT as it improves the reliability of code edits and transformations, allowing for more efficient collaboration and automation of coding tasks

Key Insight

💡 Using structured action spaces can improve the reliability and efficiency of code edits and transformations

Share This
🚀 CODESTRUCT improves LLM-based code agents with structured action spaces!

Key Takeaways

CODESTRUCT reframes codebases as structured action spaces for LLM-based code agents to operate on named AST entities

Full Article

Title: CODESTRUCT: Code Agents over Structured Action Spaces

Abstract:
arXiv:2604.05407v1 Announce Type: new Abstract: LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matching that frequently fails due to formatting drift or ambiguous patterns. We propose reframing the codebase as a structured action space where agents operate on named AST entities rather than text spans. Our framework, CODESTRUCT, provides readCode for retrieving complete syntactic units and editCode for applying syntax-validated transformations
Read full paper → ← Back to Reads