Assisted-DS
This is the official page of the paper "AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science."
We introduce AssistedDS—a benchmark for testing whether large language models (LLMs) can critically use external domain knowledge in automated tabular data science workflows. AssistedDS pairs tasks with curated helpful and adversarial guidance (e.g., feature engineering tips, cleaning steps, model choices) and evaluates whether models can adopt the good while resisting the bad. Concretely, the benchmark spans (1) synthetic datasets with known data-generating processes for precise control over what is helpful vs.
⚡ How to use Assisted-DS
Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/anluo1-assisted-dsCapabilities
Do you own Assisted-DS?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.