Model Releases
An interesting idea is to continually train specialized models on skills. This paper explores that idea. They propose SkillGym which turns h…
An interesting idea is to continually train specialized models on skills. This paper explores that idea. They propose SkillGym which turns human-written skills into 2,756 training environments with co
An interesting idea is to continually train specialized models on skills. This paper explores that idea. They propose SkillGym which turns human-written skills into 2,756 training environments with code-based checkers, then fine-tunes on 8,364 successful trajectories. After fine-tuning, Qwen3.5-35B-A3B running in Claude Code gains 19.10 points on Terminal-Bench 2.1 and 28.13 points on skill-assisted SkillsBench v1.1, where it reaches 51.47%. That is above the reported scores for Claude Sonnet 4.6 and GPT-5.4 Mini. With no skills loaded, the trained model beats the base model that has the skills in context. Paper: https://academy.dair.ai/papers/skillgym-internalizing-human-skills-into-llms-for-real-world-problem-solving-2609.27717
Related
- Exciting work from NVIDIA. (bookmark it) Interesting to see this approach to turn public Agent Skills into RL environments. Lots of exciteme…
- Really interesting paper. I recommend it to anyone interested in training agents using existing harnesses. (bookmark it) ClawGym II runs RL …
- New research from Microsoft. This one is on training computer-use agents at scale. Recent pipelines generate synthetic environments in bulk,…
- Banger paper from Tencent on environment evolution. Environment supply is becoming the main limit on agent RL. So this is worth a read. (boo…
Source: DAIR.AI (X) | 2026-09-27