We present Operand Quant, a single-agent, IDE-based architecture for autonomous machine learning engineering (MLE). Operand Quant departs from conventional multi-agent orchestration frameworks by consolidating all MLE lifecycle stages -- exploration, modeling, experimentation, and deployment -- within a single, context-aware agent. On the MLE-Benchmark (2025), Operand Quant achieved a new state-of-the-art (SOTA) result, with an overall medal rate of 0.3956 +/- 0.0565 across 75 problems -- the highest recorded performance among all evaluated systems to date. The architecture demonstrates that a linear, non-blocking agent, operating autonomously within a controlled IDE environment, can outperform multi-agent and orchestrated systems under identical constraints.
@article{arxiv.2510.11694,
title = {Operand Quant: A Single-Agent Architecture for Autonomous Machine Learning Engineering},
author = {Arjun Sahney and Ram Gorthi and Cezary Łastowski and Javier Vega},
journal= {arXiv preprint arXiv:2510.11694},
year = {2025}
}
Comments
8 pages. No figures. Evaluated on MLE-Benchmark 2025