DARE：通过分布感知检索让 LLM 智能体对齐 R 统计生态

View PDF HTML (experimental)

Abstract:Large Language Model (LLM) agents excel at automating data science workflows, yet often underutilize rigorous statistical methods in R. Existing Retrieval-Augmented Generation (RAG) approaches rely on semantic similarity, ignoring the data-distribution and structural characteristics crucial for determining a statistical method's applicability. To address this, we propose DARE (Distribution-Aware Retrieval Embedding), a representation learning framework incorporating these data characteristics into R function retrieval. Our contributions are fourfold: (i) RPKB, a curated knowledge base of 8,191 high-quality R functions; (ii) DARE, the distribution-aware retrieval framework; (iii) RCodingAgent, an R-oriented agent integrating DARE for end-to-end analysis; and (iv) RStatBench, a comprehensive benchmark of 100 statistical tasks. Experiments demonstrate that DARE improves NDCG@10 by 13.43 to 32.65 percentage points across evaluated embedding models, with a MiniLM-based DARE achieving 93.92% NDCG@10 alongside high efficiency. Furthermore, integrating DARE into RCodingAgent nearly doubles mean downstream accuracy on RStatBench, increasing from 31.8% to 62.2% across ten LLMs. This work helps bridge modern LLM automation with R's established statistical computing ecosystem.

Comments:	32 pages, 8 figures, and 3 tables
Subjects:	Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as:	arXiv:2603.04743 [cs.IR]
	(or arXiv:2603.04743v2 [cs.IR] for this version)
	https://doi.org/10.48550/arXiv.2603.04743 arXiv-issued DOI via DataCite

Submission history

From: Maojun Sun [view email]
[v1] Thu, 5 Mar 2026 02:29:54 UTC (1,760 KB)
[v2] Mon, 2 Nov 2026 16:03:21 UTC (3,853 KB)