Google's TabFM-Auto: LLM agent evolves data pipelines, lifting TabFM by 228 Elo and topping MLE-Bench
google · hf · 2026-09-30
Google introduces TabFM-Auto, pairing the TabFM tabular foundation model with an LLM agent that iteratively evolves data cleaning, feature engineering, and post-processing guided by metadata and validation feedback. Its five configurations sweep the top five on all 51 TabArena datasets, raising TabFM from 1785 to 2013 Elo; pipelines transfer to other frozen tabular models (+69 to +143 Elo). It ranks first among MLE agents on MLE-Bench's 8 tabular competitions.
Related event: Google's TabFM-Auto Lets LLM Agents Master Tabular Data Pipelines(2 posts)→
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- Effective HTML: 4.2k-star agent skills turn wireframes into self-contained interactive prototypes — tom_doerr · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16