Skip to content

feat: RL infrastructure — agent environment, trajectory export (ATIF), benchmark loaders (SWE-bench / Terminal-Bench / SWE-smith / EdgeBench), and verl / TRL adapters - #48

Open
Enderfga wants to merge 18 commits into
Rath-Team:mainfrom
Enderfga:feat/rl-infra-four-dimensions

Commits

Commits on Jul 8, 2026

Commits on Jul 12, 2026