SOURCE-LINKED INTELLIGENCE

The Imitation Game: When LLMs Learn to Reason Like Programs via Code-Centric Reasoning Data Synthesis

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

Large Language Models (LLMs) excel at programming tasks but frequently fail at deterministic, fine-grained reasoning in natural language, relying heavily on semantic approximations rather than robust symbolic execution. To bridge this gap, we propose MIMIC, a framework that leverages executable code as a rigorous medium for reasoning data synthesis. MIMIC fundamentally transforms algorithms into verifiable reasoning trajectories through narrative fusion, code-guided test synthesis, and dynamic code instrumentation. Crucially, these explicit intermediate execution states naturally form a Code-I

Read original source ↗ Open in workspace

recordType

paper

region

Global