WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
Ranking
Overall
86
Content
95
Popularity
65
Observed public metrics from 1 member.
Merged summary
TL;DR - WikiSkill is a framework that consolidates agents’ execution experience into a persistent wiki used to evolve reusable skills. It improves agent performance and enables skills to transfer across models and model families.
- Separates raw execution histories, accumulated knowledge, and executable skills while continuously updating the shared wiki.
- Consistently outperforms prior skill-evolution methods across diverse benchmarks and models, and beats no-skill baselines in most tested settings.
- Evolved skills complement model scaling: larger models generally gain more, while smaller skill-equipped models can outperform substantially larger models without skills.
- Ablations identify persistent knowledge accumulation as critical; skills can also transfer effectively and sometimes outperform skills evolved by the target model itself.
Sources (1)
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
Public signals
Hugging Face upvotes 34
TL;DR - WikiSkill is a framework that consolidates agents’ execution experience into a persistent wiki used to evolve reusable skills. It improves agent performance and enables skills to transfer across models and model families.
- Separates raw execution histories, accumulated knowledge, and executable skills while continuously updating the shared wiki.
- Consistently outperforms prior skill-evolution methods across diverse benchmarks and models, and beats no-skill baselines in most tested settings.
- Evolved skills complement model scaling: larger models generally gain more, while smaller skill-equipped models can outperform substantially larger models without skills.
- Ablations identify persistent knowledge accumulation as critical; skills can also transfer effectively and sometimes outperform skills evolved by the target model itself.