Team releases 2,756 verifiable agent skill training environments
SkillGym turns human skill workflows into verifiable training environments and open-sources them; the gains are self-tested and await external checks.
Original event 2026-09-24
A research team has released SkillGym, a framework that turns human-written agent skills into verifiable training environments, and open-sourced 2,756 of them.
The environments span 12 task categories and come with 8,364 successful trajectories, usable for supervised fine-tuning and outcome-reward reinforcement learning. The paper's own tests report that fine-tuning lifts Qwen3.5-35B-A3B by 19.10 percentage points on Terminal-Bench 2.1.
The abstract offers no third-party reproduction, and the comparison scores for Claude Sonnet 4.6 and others are values cited by the paper; the environments' quality awaits external use.