ST-Raptor: An Agentic System for Semi-Structured Table QA
Jinxiu Qu, Zirui Tang, Hongzhang Huang, Boyu Niu, Wei Zhou, Jiannan Wang, Yitong Song, Guoliang Li, Xuanhe Zhou, Fan Wu

TL;DR
ST-Raptor is an interactive system that improves semi-structured table question answering by combining visual editing, structural modeling, and agent-driven query resolution, outperforming existing methods in accuracy and usability.
Contribution
It introduces ST-Raptor, a novel agentic system that enhances semi-structured table QA through interactive analysis and structural modeling, addressing limitations of prior approaches.
Findings
Outperforms existing methods in accuracy on benchmark datasets.
Provides a user-friendly, interactive environment for table analysis.
Demonstrates effectiveness on real-world semi-structured tables.
Abstract
Semi-structured table question answering (QA) is a challenging task that requires (1) precise extraction of cell contents and positions and (2) accurate recovery of key implicit logical structures, hierarchical relationships, and semantic associations encoded in table layouts. In practice, such tables are often interpreted manually by human experts, which is labor-intensive and time-consuming. However, automating this process remains difficult. Existing Text-to-SQL methods typically require converting semi-structured tables into structured formats, inevitably leading to information loss, while approaches like Text-to-Code and multimodal LLM-based QA struggle with complex layouts and often yield inaccurate answers. To address these limitations, we present ST-Raptor, an agentic system for semi-structured table QA. ST-Raptor offers an interactive analysis environment that combines visual…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHandwritten Text Recognition Techniques · Web Data Mining and Analysis · Topic Modeling
