← Back to Benchmarks
simmediumrlmetric · varies

Self-Execution Simulation Improves Coding Models

Description

A promising research direction in enabling LLMs to generate consistently correct code involves addressing their inability to properly estimate program execution, particularly for code they generate. In this work, we demonstrate that Code LLMs can be trained to simulate program execution in a step-by-step manner and that this capability can be leveraged to improve competitive programming performance. Our approach combines supervised fine-tuning on natural language execution traces, textual explan

Source

http://arxiv.org/abs/2604.03253v1