DRAMA: Unifying Data Retrieval and Analysis for Open-Domain Analytic Queries

TL;DR

DRAMA introduces an end-to-end system that unifies data retrieval, transformation, and analysis to answer open-domain analytic queries efficiently, supported by a new benchmark and a multi-agent system that outperforms existing methods.

Contribution

This work presents DRAMA, a novel paradigm and system that integrates data collection, transformation, and reasoning for open-domain analytics, along with a benchmark and a multi-agent implementation.

Findings

DRAMA-Bot achieves 86.5% accuracy on DRAMA-Bench.

DRAMA-Bot reduces cost to less than one-sixth of baseline methods.

DRAMA outperforms state-of-the-art agents by up to 6.9 times in accuracy.

Abstract

Manually conducting real-world data analyses is labor-intensive and inefficient. Despite numerous attempts to automate data science workflows, none of the existing paradigms or systems fully demonstrate all three key capabilities required to support them effectively: (1) open-domain data collection, (2) structured data transformation, and (3) analytic reasoning. To overcome these limitations, we propose DRAMA, an end-to-end paradigm that answers users' analytic queries in natural language on large-scale open-domain data. DRAMA unifies data collection, transformation, and analysis as a single pipeline. To quantitatively evaluate system performance on tasks representative of DRAMA, we construct a benchmark, DRAMA-Bench, consisting of two categories of tasks: claim verification and question answering, each comprising 100 instances. These tasks are derived from real-world applications that have gained significant public attention and require the retrieval and analysis of open-domain data. We develop DRAMA-Bot, a multi-agent system designed following DRAMA. It comprises a data retriever that collects and transforms data by coordinating the execution of sub-agents, and a data analyzer that performs structured reasoning over the retrieved data. We evaluate DRAMA-Bot on DRAMA-Bench together with five state-of-the-art baseline agents. DRAMA-Bot achieves 86.5% task accuracy at a cost of $0.05, outperforming all baselines with up to 6.9 times the accuracy and less than 1/6 of the cost. DRAMA is publicly available at https://github.com/uiuc-kang-lab/drama.