CEDAR: Context Engineering for Agentic Data Science

TL;DR

CEDAR is an innovative application that automates data science tasks using agentic LLMs, addressing challenges like complexity and context management through structured prompts and iterative code generation.

Contribution

The paper introduces a novel agentic system for automating data science workflows with structured prompts, multi-agent coordination, and efficient context handling.

Findings

Successfully applied to canonical Kaggle challenges.

Effective context engineering improves task handling.

Fault tolerance via iterative code generation.

Abstract

We demonstrate CEDAR, an application for automating data science (DS) tasks with an agentic setup. Solving DS problems with LLMs is an underexplored area that has immense market value. The challenges are manifold: task complexities, data sizes, computational limitations, and context restrictions. We show that these can be alleviated via effective context engineering. We first impose structure into the initial prompt with DS-specific input fields, that serve as instructions for the agentic system. The solution is then materialized as an enumerated sequence of interleaved plan and code blocks generated by separate LLM agents, providing a readable structure to the context at any step of the workflow. Function calls for generating these intermediate texts, and for corresponding Python code, ensure that data stays local, and only aggregate statistics and associated instructions are injected into LLM prompts. Fault tolerance and context management are introduced via iterative code generation and smart history rendering. The viability of our agentic data scientist is demonstrated using canonical Kaggle challenges.