# "Skill Issues'': Data-Centric Optimization of Lakehouse Agents

arXiv: https://arxiv.org/abs/2606.01185 · HTML: https://mlsanity.com/paper/2606.01185/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 46 references that are in the map.
- First posted on arXiv 31 May 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 19 of 19)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [Language Models Learn to Mislead Humans via RLHF](https://mlsanity.com/paper/2409.12822/) (2024)
- [EvoX: Meta-Evolution for Automated Discovery](https://mlsanity.com/paper/2602.23413/) (2026)
- [A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?](https://mlsanity.com/paper/2408.05109/) (2024)
- [Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems](https://mlsanity.com/paper/2604.14228/) (2026)
- [Optimizing Model Selection for Compound AI Systems](https://mlsanity.com/paper/2502.14815/) (2025)
- [SkillReducer: Optimizing LLM Agent Skills for Token Efficiency](https://mlsanity.com/paper/2603.29919/) (2026)
- [Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First](https://mlsanity.com/paper/2509.00997/) (2025)
- [Theory of Mind in Large Language Models: Assessment and Enhancement](https://mlsanity.com/paper/2505.00026/) (2025)
- [Large Language Model-based Data Science Agent: A Survey](https://mlsanity.com/paper/2508.02744/) (2025)
- [Professional Software Developers Don't Vibe, They Control: AI Agent Use for Coding in 2025](https://mlsanity.com/paper/2512.14012/) (2025)
- [SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering](https://mlsanity.com/paper/2604.09297/) (2026)
- [Skill-R1: Agent Skill Evolution via Reinforcement Learning](https://mlsanity.com/paper/2605.09359/) (2026)
- [Reproducible data science over data lakes: replayable data pipelines with Bauplan and Nessie](https://mlsanity.com/paper/2404.13682/) (2024)
- [Reasoning-Driven Synthetic Data Generation and Evaluation](https://mlsanity.com/paper/2603.29791/) (2026)
- [Towards Machine Theory of Mind with Large Language Model-Augmented Inverse Planning](https://mlsanity.com/paper/2507.03682/) (2025)
- [Building a Correct-by-Design Lakehouse. Data Contracts, Versioning, and Transactional Pipelines for Humans and Agents](https://mlsanity.com/paper/2602.02335/) (2026)

## Built on by (most cited first, 1 of 1)

- [GitLake: Git-for-data for the agentic lakehouse](https://mlsanity.com/paper/2607.08319/) (2026)

## Abstract (arXiv)

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 hundreds of tasks, optimized skills improve held-out reward by up to 28.6%. These results suggest that write-path data workflows provide a useful substrate for optimizing agent skills beyond read-only tasks.