🛰️ Daily AI Frontier
‹ back to 2026-09-24

SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving

Research LLM Agents

Ranking

Overall 85
Content 100
Popularity N/A

No observed public metrics; popularity remains neutral/archived.

Merged summary

TL;DR - SkillGym converts human-authored agent workflows into verifiable training environments, enabling LLMs to internalize reusable problem-solving skills rather than rely on inference-time instructions. Fine-tuning on verified trajectories substantially improved a 35B model across agent and terminal benchmarks.

  • The released dataset includes 2,756 environments across 12 categories and 8,364 successful multi-model trajectories, averaging 49 tool calls each.
  • Tasks use code-based outcome checkers and contrastive executions to verify both correctness and dependence on the target skill.
  • Supervised fine-tuning improved Qwen3.5-35B-A3B by 199 Elo on GDPval-AA v2 and 19.10 percentage points on Terminal-Bench 2.1.
  • The resulting SkillGym-Agent reached 51.47% on skill-assisted SkillsBench and retained gains without external skills, suggesting internalized procedural competence.

Sources (1)

SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving

arXiv cs.CL Zhilong Ge, Yuting Shao, Yutao Yang, Yuxuan Cai, Jie Zhou, Kai Chen, Bo Zhang, Qin Chen, Liang He 2026-09-23 arXiv:2609.27717
Public signals N/A
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-26 14:14:22.800982 UTC

TL;DR - SkillGym converts human-authored agent workflows into verifiable training environments, enabling LLMs to internalize reusable problem-solving skills rather than rely on inference-time instructions. Fine-tuning on verified trajectories substantially improved a 35B model across agent and terminal benchmarks.

  • The released dataset includes 2,756 environments across 12 categories and 8,364 successful multi-model trajectories, averaging 49 tool calls each.
  • Tasks use code-based outcome checkers and contrastive executions to verify both correctness and dependence on the target skill.
  • Supervised fine-tuning improved Qwen3.5-35B-A3B by 199 Elo on GDPval-AA v2 and 19.10 percentage points on Terminal-Bench 2.1.
  • The resulting SkillGym-Agent reached 51.47% on skill-assisted SkillsBench and retained gains without external skills, suggesting internalized procedural competence.
item →