# Monte Carlo Tree Search for Table-to-Multimodal Report Generation

arXiv: https://arxiv.org/abs/2608.04071 · HTML: https://mlsanity.com/paper/2608.04071/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Builds on (most cited first, 14 of 14)

- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [TabFact: A Large-scale Dataset for Table-based Fact Verification](https://mlsanity.com/paper/1909.02164/) (2019)
- [ToTTo: A Controlled Table-To-Text Generation Dataset](https://mlsanity.com/paper/2004.14373/) (2020)
- [FeTaQA: Free-form Table Question Answering](https://mlsanity.com/paper/2104.00369/) (2021)
- [TableGPT2: A Large Multimodal Model with Tabular Data Integration](https://mlsanity.com/paper/2411.02059/) (2024)
- [MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents](https://mlsanity.com/paper/2601.12346/) (2026)
- [Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework](https://mlsanity.com/paper/2506.02454/) (2025)
- [MEBench: Benchmarking Large Language Models for Cross-Document Multi-Entity Question Answering](https://mlsanity.com/paper/2502.18993/) (2025)
- [Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training](https://mlsanity.com/paper/2603.12246/) (2026)
- [VIS-Shepherd: Constructing Critic for LLM-based Data Visualization Generation](https://mlsanity.com/paper/2506.13326/) (2025)
- [Simplifying Data Integration: SLM-Driven Systems for Unified Semantic Queries Across Heterogeneous Databases](https://mlsanity.com/paper/2504.05634/) (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)
- [EvidFuse: Writing-Time Evidence Learning for Consistent Text-Chart Data Reporting](https://mlsanity.com/paper/2601.05487/) (2026)

## Built on by (most cited first, 3 of 3)

- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [EidosDoc: Implicit Structure Encoding for Cost-Effective Semi-Structured Document QA](https://mlsanity.com/paper/2609.27784/) (2026)
- [Structured Composition of Verifiable Atomic Insights for Table-to-Report Generation](https://mlsanity.com/paper/2610.03525/) (2026)

## Abstract (arXiv)

Automatically generating professional multimodal reports comprising both textual analysis and visual charts from structured tabular data is a critical challenge in data intelligence. Existing methods suffer from fixed linear pipelines and isolated subtask processing, which hinder joint optimization of factual accuracy, visual quality, and narrative coherence. To address these issues, this paper proposes MCTS-Report, a Monte Carlo Tree Search (MCTS)-driven framework that formulates multimodal table-to-report generation as a progressive construction process over a structured search space. The core idea is to decompose report generation into atomic actions, including chapter planning, visualization task identification, chart generation, insight organization, and narrative refinement, each executed by an LLM based on dynamic reasoning conditioned on the current report state. We use an LLM to generate step-by-step reasoning and actions during MCTS, storing the reasoning trajectory in each node for context-aware, coherent report construction. To guide the search, we design a multi-dimensional reward function that jointly evaluates numerical fact consistency (via SQL), chart quality, chart-text alignment, and structural completeness, while incorporating a diversity penalty to suppress repeated charts and a precondition check to prune invalid actions. We also construct MMRBench, a comprehensive benchmark comprising real-world tables from six domains, paired with expert-refined reference report structures and verifiable key insights. Experiments on MMRBench demonstrate that MCTS-Report significantly outperforms strong baselines across structural completeness, numerical accuracy, chart-text alignment, and insight novelty, achieving a 77.9 overall score.