table-reasoning

TabClaw is an open-source interactive AI agent for spreadsheet manipulation and table reasoning that uses LLMs to automate data analysis, support multi-table reasoning, and adapt to user preferences through memory and skill extraction.

CRAFT is a unified counterfactual reasoning framework that improves tabular question answering and fact verification by constructing both original and counterfactual statements, extracting evidence from bidirectional reasoning paths, and integrating them via a weighted mechanism. Experiments show consistent improvements over baselines on WikiTQ and TabFact datasets.

This paper proposes EcoTab, a table-aware stepwise routing framework that separately estimates uncertainty for table tokens and text tokens to dynamically route reasoning steps between small and large models, achieving a better accuracy-efficiency trade-off on table reasoning tasks.

Introduces TableVista, a comprehensive benchmark for evaluating foundation models on multimodal table reasoning under visual and structural complexity, comprising 3,000 problems expanded into 30,000 multimodal samples. Evaluation of 29 models reveals performance degradation on complex layouts and vision-only settings.