NVIDIA 发布 Skill2Env：将公开 Agent Skills 编译为 RL 环境生成近 8000 条训练任务

md 并拆分工作流，Codex creator 为每个任务构建程序化测试和行为 rubric。从约 3400 个爬取的 Skills 中产出 7971 条任务，覆盖 13 个领域，软件工程占比不到四分之一，用 GPT-5.

6 Sol 生成的 API 花费超过 9 万美元。Qwen3.

8-27B 经过 300 步结果导向 RL 训练后，Terminal-Bench 2.1 成绩从 49.

4% 提升到 54.1%，S2EBench pass@1 从 33.

4% 提升到 37.7%。

加入 rubric 奖励在基准上增益较小（Terminal-Bench 2.1 为 50.

1%），但人类偏好的模型轨迹占比从 54.5% 升至 73.

0%。

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://t.co/DYm5hevsHd

Chat with Paper: https://t.co/WSSNWE3erY

本条情报归属 AITOP「论文」核心栏目，重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」「中美大模型技术代差与商业化对照」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：Skill2Env、NVIDIA、Qwen、Codex，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明：本文原始线索采编自「DAIR.AI」（@dair_ai），经 AITOP 多维评分管线结构化提炼。截至目前，全网已有 9 家独立信源对该事件进行交叉印证与跟进报道（含 shao__meng、NVIDIA AI、arXiv cs.LG 等），属于近期高关注度行业信号。