MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonstrate advanced capabilities in reasoning, coding, and engineering tasks, it is increasingly important to understand whether they can discover such methods rather than only apply existing ones. We introduce MLS-Bench, a benchmark for evaluating whether AI systems can invent generalizable and scalable ML methods. MLS-Bench contains 140 tasks across 12 domains, each requiring an agent to improve one targeted component of an ML system or algorithm and demonstrate that the improvement generalizes across controlled settings and scales. We find th...
| Authors | Bohan Lyu, Yucheng Yang, Siqiao Huang et al. |
|---|---|
| Primary category | cs.LG |
| Published | 9 May 2026 |
| Last updated at source | 6 July 2026 |
Connected in the knowledge graph
- Bohan22/MLS-Bench-TasksDataset · cited by
Models and datasets referencing this paper
- Bohan22/MLS-Bench-TasksDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.