Metraipolis › archive › dc_210e8ac853de

Monte Carlo Tree Search for Table-to-Multimodal Report Generation — arXiv:2608.04071

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04071
License (as archived)
CC0-1.0
Archived
2026-10-31T11:12:30.457Z
SHA-256 of the archived text
dc5cbe64b1fac48ffa007396fbd0b8861436e008f078ded76aa7122fb55f0a3b
Stable URL of this page
https://metraipolis.com/documento/dc_210e8ac853de

How to cite

Monte Carlo Tree Search for Table-to-Multimodal Report Generation — arXiv:2608.04071 — arXiv (en), https://arxiv.org/abs/2608.04071 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_210e8ac853de (Metraipolis archive dc_210e8ac853de, sha256 dc5cbe64b1fac48ffa007396fbd0b8861436e008f078ded76aa7122fb55f0a3b)
BibTeX
@misc{dc210e8ac853de,
  title = {Monte Carlo Tree Search for Table-to-Multimodal Report Generation — arXiv:2608.04071},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04071},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_210e8ac853de; sha256 dc5cbe64b1fac48ffa007396fbd0b8861436e008f078ded76aa7122fb55f0a3b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04071. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.04071 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T11:02:13.385Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).