TaREx: Reinforcement Learning for Code-Driven Table Reasoning

Abstract

Automatically solving table reasoning tasks remains challenging due to three main factors: (1) diverse and hierarchical table structures that hinder comprehension, (2) the heavy reliance on complex logical and numerical reasoning—which makes purely text-based methods prone to hallucinations—and (3) the necessity of multi-step processing to handle intricate tasks involving multiple and lengthy tables. To address these challenges, we introduce TaREx, a novel framework that unifies table representation, integrates code-driven execution, and supports interactive multi-step reasoning. TaREx employs a reinforcement learning-based training pipeline to optimize its reasoning policy for complex tasks. Experimental results show that TaREx achieves state-of-the-art performance across a wide range of table reasoning benchmarks, both in-domain and out-of-domain. These include fundamental tasks such as table question answering (TQA) and table fact verification (TFV), as well as advanced tabular data analysis tasks. The results highlight TaREx’s effectiveness and scalability in advancing automated table reasoning.