{"ID":2921696,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-03T05:56:00.181519634Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.01185","arxiv_id":"2606.01185","title":"\"Skill issues'': data-centric optimization of lakehouse agents","abstract":"Coding agents are becoming users of data infrastructure, but their success depends not only on model quality: it also depends on the skills and environment files that teach agents how to use a system. We study how to optimize these artifacts for agents operating on a branching lakehouse, Bauplan. In our setting, headless APIs and Git-like data primitives expose data workflows through code, branches, commits, and merges. Our central observation is that a branching lakehouse turns data-agent evaluation from an output-matching problem into a state-verification problem: agent-generated pipeline code induces concrete, inspectable lakehouse changes. We present a data-centric optimization pipeline that generates task-verifier pairs, executes candidate skills in isolated sandboxes, and scores trajectories using both trace-level signals and programmatic checks over lakehouse state. In a preliminary evaluation on 25 tasks, optimized skills improve accuracy by 31.9%. These results suggest that write-path data workflows provide a useful substrate for optimizing agent skills beyond read-only tasks.","short_abstract":"Coding agents are becoming users of data infrastructure, but their success depends not only on model quality: it also depends on the skills and environment files that teach agents how to use a system. We study how to optimize these artifacts for agents operating on a branching lakehouse, Bauplan. In our setting, headle...","url_abs":"https://arxiv.org/abs/2606.01185","url_pdf":"https://arxiv.org/pdf/2606.01185v1","authors":"[\"Nicole Rose Schneider\",\"Davide Ghilardi\",\"Giacomo Piccinini\",\"Jacopo Tagliabue\"]","published":"2026-05-31T11:58:04Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[]","has_code":false}