HomeTagsMini-SWE-Agent

Mini-SWE-Agent

Same AI Model Scores 33% or 62% Depending on Its Coding Tools

Hugging Face's FineEnvs team has released an open framework that turns unmodified coding-agent harnesses such as Claude Code, Codex and OpenCode into reinforcement-learning environments. In its own tests, one small model scored 62% in one harness and 33% in another. What a harness is, how the training works, and what the results do and do not show.

Just in

Latest

No posts to display

Timeline

Every story in Mini-SWE-Agent, grouped by month.

October 2026

Latest on TSN

Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.