llmflow: Reasoning and Acting Workflow for Automated Data Analysis

CRAN: Contributed Packages 2026 Dataset Open access

Read full text
Authors: Zaoqu Liu
DOI: 10.32614/cran.package.llmflow
Cited by: 1

Abstract

Provides a framework for integrating Large Language Models (LLMs) with R programming through workflow automation. Built on the ReAct (Reasoning and Acting) architecture, enables bi-directional communication between LLMs and R environments. Features include automated code generation and execution, intelligent error handling with retry mechanisms, persistent session management, structured JSON output validation, and context-aware conversation management.

Publication details

Journal / source
CRAN: Contributed Packages
Publisher
The R Foundation
Publication date
31 January 2026
Document type
Dataset