Semi-Formal Code Reasoning
Structured reasoning for code verification, fault localization, and semantic analysis — without running tests. Based on the Agentic Code Reasoning paper which showed 10-12pp accuracy gains over unstructured chain-of-thought.
Overview
Standard LLM reasoning about code makes unsupported claims — assumes function behavior without tracing, skips edge cases, concludes equivalence without checking all paths.
Semi-formal reasoning
[Description truncada. Veja o README completo no GitHub.]