arXiv cs.AIMonday · May 25, 2026FREE

From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills

agentsskillsllmevaluation

A new study from arXiv (2605.23899) systematically examines the full lifecycle of model-generated agent skills: experience generation, skill extraction, and skill consumption. The researchers built a utility-grounded evaluation framework covering five diverse agentic task domains. They found that model-generated skills are beneficial on average but exhibit non-trivial negative transfer, meaning they can sometimes harm performance. Notably, neither extractors nor target agents behave uniformly; a model can be a strong extractor yet a weak consumer, or vice versa. The study highlights the need for careful evaluation of skill extraction methods and their downstream impact.

// why it matters

Developers must evaluate both skill extraction and consumption to avoid negative transfer.

Sources

Primary · arXiv cs.AI
▸ Read original at arxiv.org

Like this? Get the next digest.

From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills — aigest.dev