Exciting work from NVIDIA. (bookmark it) Interesting to see this approach to turn public Agent Skills into RL environments. Lots of exciteme…

Exciting work from NVIDIA. (bookmark it) Interesting to see this approach to turn public Agent Skills into RL environments. Lots of excitement around RL environments so this is a great read. Skill2Env compiles each Skill into executable terminal tasks. A Codex planner reads the SKILL.md bundle, researches related public assets and splits the Skill into workflows. A Codex creator then builds each task with programmatic tests and a behavioral rubric taken from the Skill's own quality criteria. From about 3.4k crawled Skills, the pipeline produced 7,971 tasks across 13 domains, with software engineering under a quarter of the corpus. Generating them with GPT-5.6 Sol cost over $90k in API usage. After 300 steps of outcome-only RL, Qwen3.8-27B improved from 49.4% to 54.1% on Terminal-Bench 2.1 and from 33.4% to 37.7% pass@1 on S2EBench, their hand-verified held-out benchmark. Adding the rubric to the reward gave smaller benchmark gains, 50.1% on Terminal-Bench 2.1. Given the source SKILL.md, a judge preferred the rubric-trained model's trajectories over the base model's on 73.0% of tasks, against 54.5% for the outcome-only model. Paper: https://github.com/NVlabs/Skill2Env/blob/main/paper/Skill2Env_arXiv.pdf Chat with Paper: https://academy.dair.ai/papers/reinforcing-agents-with-collective-skills

Source: DAIR.AI (X) | 2026-09-23