This paper presents the Advanced Reasoning and Transformation Engine for Multi-Step Insight Synthesis in Data Analytics (ARTEMIS-DA), a novel framework designed to augment Large Language Models (LLMs) for solving complex, multi-step data analytics tasks. ARTEMIS-DA integrates three core components: the Planner, which dissects complex user queries into structured, sequential instructions encompassing data preprocessing, transformation, predictive modeling, and visualization; the Coder, which dynamically generates and executes Python code to implement these instructions; and the Grapher, which interprets generated visualizations to derive actionable insights. By orchestrating the collaboration between these components, ARTEMIS-DA effectively manages sophisticated analytical workflows involving advanced reasoning, multi-step transformations, and synthesis across diverse data modalities. The framework achieves state-of-the-art (SOTA) performance on benchmarks such as WikiTableQuestions and TabFact, demonstrating its ability to tackle intricate analytical tasks with precision and adaptability. By combining the reasoning capabilities of LLMs with automated code generation and execution and visual analysis, ARTEMIS-DA offers a robust, scalable solution for multi-step insight synthesis, addressing a wide range of challenges in data analytics.

翻译：本文提出了面向数据分析中多步骤洞察合成的高级推理与转换引擎（ARTEMIS-DA），这是一个旨在增强大型语言模型（LLMs）以解决复杂多步骤数据分析任务的新型框架。ARTEMIS-DA集成了三个核心组件：规划器（Planner），负责将复杂的用户查询分解为包含数据预处理、转换、预测建模和可视化的结构化顺序指令；编码器（Coder），动态生成并执行Python代码以实现这些指令；以及绘图器（Grapher），通过解读生成的可视化结果来推导可操作的洞察。通过协调这些组件之间的协作，ARTEMIS-DA能够有效管理涉及高级推理、多步骤转换以及跨多种数据模态合成的复杂分析工作流。该框架在WikiTableQuestions和TabFact等基准测试中达到了最先进的性能，证明了其以精确性和适应性处理复杂分析任务的能力。通过将LLMs的推理能力与自动化代码生成执行以及视觉分析相结合，ARTEMIS-DA为多步骤洞察合成提供了一个稳健、可扩展的解决方案，应对数据分析中的广泛挑战。