Regression Language Models for Code
Abstract
We study code-to-metric regression: predicting numeric outcomes of code executions, a challenging task due to the open-ended nature of programming languages. While prior methods have resorted to heavy and domain-specific feature engineering, we show that a single unified Regression Language Model (RLM) using a frozen LLM encoder can simultaneously predict directly from text, (i) the memory footprint of code across multiple high-level languages such as Python and C++, (ii) the latency of Triton GPU kernels, and (iii) the accuracy and speed of trained neural networks represented in ONNX. In particular, a relatively small 300M parameter RLM based on T5Gemma, obtains 0.9 Spearman-rank on competitive programming submissions from APPS, and a single unified model achieves 0.5 average Spearman-rank across 17 separate languages from CodeNet. Furthermore, the RLM can obtain the highest average Kendall-Tau of 0.46 on five classic NAS design spaces previously dominated by graph neural networks, and simultaneously predict architecture latencies on numerous hardware platforms.
Keywords
Cite
@article{arxiv.2509.26476,
title = {Regression Language Models for Code},
author = {Yash Akhauri and Xingyou Song and Arissa Wongpanich and Bryan Lewandowski and Mohamed S. Abdelfattah},
journal= {arXiv preprint arXiv:2509.26476},
year = {2026}
}
Comments
Published in International Conference on Machine Learning (ICML) 2026