# Structured Composition of Verifiable Atomic Insights for Table-to-Report Generation

arXiv: https://arxiv.org/abs/2610.03525 · HTML: https://mlsanity.com/paper/2610.03525/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 45 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 30 of 30)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [ToTTo: A Controlled Table-To-Text Generation Dataset](https://mlsanity.com/paper/2004.14373/) (2020)
- [HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data](https://mlsanity.com/paper/2004.07347/) (2020)
- [FeTaQA: Free-form Table Question Answering](https://mlsanity.com/paper/2104.00369/) (2021)
- [InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks](https://mlsanity.com/paper/2401.05507/) (2024)
- [TableBench: A Comprehensive and Complex Benchmark for Table Question Answering](https://mlsanity.com/paper/2408.09174/) (2024)
- [DataSciBench: An LLM Agent Benchmark for Data Science](https://mlsanity.com/paper/2502.13897/) (2025)
- [DABstep: Data Agent Benchmark for Multi-step Reasoning](https://mlsanity.com/paper/2506.23719/) (2025)
- [InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation](https://mlsanity.com/paper/2407.06423/) (2024)
- [MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents](https://mlsanity.com/paper/2601.12346/) (2026)
- [InsightLens: Augmenting LLM-Powered Data Analysis with Interactive Insight Management and Navigation](https://mlsanity.com/paper/2404.01644/) (2024)
- [MEBench: Benchmarking Large Language Models for Cross-Document Multi-Entity Question Answering](https://mlsanity.com/paper/2502.18993/) (2025)
- [MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark](https://mlsanity.com/paper/2506.05587/) (2025)
- [SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graph](https://mlsanity.com/paper/2503.01346/) (2025)
- [DataCross: A Unified Benchmark and Agent Framework for Cross-Modal Heterogeneous Data Analysis](https://mlsanity.com/paper/2601.21403/) (2026)
- [Simplifying Data Integration: SLM-Driven Systems for Unified Semantic Queries Across Heterogeneous Databases](https://mlsanity.com/paper/2504.05634/) (2025)
- [Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models](https://mlsanity.com/paper/2602.02039/) (2026)
- [UniDataBench: Evaluating Data Analytics Agents Across Structured and Unstructured Data](https://mlsanity.com/paper/2511.01625/) (2025)
- [AnnoRetrieve: Efficient Structured Retrieval for Unstructured Document Analysis](https://mlsanity.com/paper/2604.02690/) (2026)
- [LightKGG: Simple and Efficient Knowledge Graph Generation from Textual Data](https://mlsanity.com/paper/2510.23341/) (2025)
- [InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents](https://mlsanity.com/paper/2511.22884/) (2025)
- [DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering](https://mlsanity.com/paper/2603.11798/) (2026)
- [Monte Carlo Tree Search for Table-to-Multimodal Report Generation](https://mlsanity.com/paper/2608.04071/) (2026)
- [WebDS: An End-to-End Benchmark for Web-based Data Science](https://mlsanity.com/paper/2508.01222/) (2025)
- [FreshTab: Sourcing Fresh Data for Table-to-Text Generation Evaluation](https://mlsanity.com/paper/2510.13598/) (2025)
- [MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data](https://mlsanity.com/paper/2512.13297/) (2025)
- [Structure then Query: Enabling Precise Analytical Queries over Unstructured Documents](https://mlsanity.com/paper/2608.13384/) (2026)
- [EidosDoc: Implicit Structure Encoding for Cost-Effective Semi-Structured Document QA](https://mlsanity.com/paper/2609.27784/) (2026)

## Abstract (arXiv)

Table-to-report generation refers to the task of automatically generating article-level analyt- ical reports from relational tables and is an essential capability for automated data science and decision support. Its central challenge lies in systematically discovering verifiable com- posite insights across tables, attributes, and analytical perspectives, and organizing them into coherent, complete, and traceable evidence chains. Existing methods primarily rely on sequential, reactive data agents or direct Large Language Model(LLM) generation. They suffer from exploration bias: early local observations constrain subsequent actions, causing models to focus prematurely on local analyzes and miss cross-table or cross-dimensional evidence. We propose ComInsight, which reformulates insight discovery as the composition of atomic evidences. We first define an atomic insight as the smallest executable analytical unit conforming to a predefined analysis pattern and enumerate all valid atomic insights from database schema and content. These atoms are then organized into a multi-relational insight graph, where nodes represent verified data facts and edges encode logical, temporal, or hierarchical relations. Finally, a set of composition operators systematically fuses atomic nodes into higher-order composite conclusions. Every composite output is accompanied by executable SQL and fine-grained provenance, ensuring full verifiability. Across three benchmarks InsightBench, DDR-Bench, and T2R-Bench, ComInsight consistently outperforms strong baselines in factual correctness, novelty, and structural completeness. We believe ComInsight offers a reliable, efficient, and explainable path toward table-to-report generation.