OpenSkill: Open-World Self-Evolution for LLM Agents

Key points

Open-world self-evolution is defined as the process of building skills and verification signals at the same time from task prompts alone.
In the open world, grounding knowledge and verification anchors are acquired independently.
Self-built virtual tasks are used for skill refinement, with no target supervision at all.
On SkillsBench, it improves by 8.9 percent over the previous strongest baseline.
The skills transfer across models, so the same effect applies even to weaker models.
The self-built verifier covers 88.9 percent of the intent represented in the ground truth.

External research summaries. These are not HDATF publications or measured product results.