PolymathPolymath
Horizon-SWEBlogAbout
LinkedIn·X
Get in touch
Privacy·Terms
© 2026 Polymath AI Labs
Polymath Logo
PolymathPolymath
February 2, 2026

Introducing Horizon-SWE: Evaluating the Performance of AI Agents on End-to-End Software Engineering Workflows

A benchmark for multi-tool, long-horizon software engineering tasks in production grade systems.

January 10, 2026

Towards Greater Reliability and Autonomy in Software Engineering Agents

AI coding agents have become remarkably capable at programming - starting from autocomplete, to single-file edits, to making changes across the entire repository. However, true software engineering requires more than just writing code.