AI RESEARCH
CODESTRUCT: Code Agents over Structured Action Spaces
arXiv CS.AI
•
ArXi:2604.05407v1 Announce Type: new 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 to semantic program elements.