Excited to share our work at @GoogleDeepMind!

We propose Naturalized Execution Tuning (NExT), a self-training method that drastically improves the LLM's ability to reason about code execution, by learning to inspect execution traces and generate chain-of-thought rationales 🧵👇 To help LLMs better understand program execution traces, we propose an inline trace representation, which encodes execution states as update variable values within inline comments. We also add the ordinal numbers "(0) ..." to denote execution order [2/n]