DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval

TL;DR

This paper introduces DARE, a distribution-aware retrieval model that enhances R package function retrieval for LLM agents by incorporating data distribution information, leading to improved accuracy and more reliable statistical analysis automation.

Contribution

The paper presents DARE, a novel embedding model that fuses data distribution features with function metadata, and introduces RPKB and RCodingAgent for improved R statistical workflow automation.

Findings

DARE achieves an NDCG@10 of 93.47%, outperforming existing models by up to 17%.

Integrating DARE into LLM agents significantly improves downstream statistical analysis tasks.

DARE uses fewer parameters while providing superior retrieval relevance.

Abstract

Large Language Model (LLM) agents can automate data-science workflows, but many rigorous statistical methods implemented in R remain underused because LLMs struggle with statistical knowledge and tool retrieval. Existing retrieval-augmented approaches focus on function-level semantics and ignore data distribution, producing suboptimal matches. We propose DARE (Distribution-Aware Retrieval Embedding), a lightweight, plug-and-play retrieval model that incorporates data distribution information into function representations for R package retrieval. Our main contributions are: (i) RPKB, a curated R Package Knowledge Base derived from 8,191 high-quality CRAN packages; (ii) DARE, an embedding model that fuses distributional features with function metadata to improve retrieval relevance; and (iii) RCodingAgent, an R-oriented LLM agent for reliable R code generation and a suite of statistical analysis tasks for systematically evaluating LLM agents in realistic analytical scenarios. Empirically, DARE achieves an NDCG at 10 of 93.47%, outperforming state-of-the-art open-source embedding models by up to 17% on package retrieval while using substantially fewer parameters. Integrating DARE into RCodingAgent yields significant gains on downstream analysis tasks. This work helps narrow the gap between LLM automation and the mature R statistical ecosystem.