Metraipolis › archive › dc_fc89d0eba8e2

WeaveData: A Multimodal Data Analysis System with Self-Critiquing and Self-Evolving LLM Plans — arXiv:2609.34764

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34764
License (as archived)
CC0-1.0
Archived
2026-10-07T21:02:55.675Z
SHA-256 of the archived text
c34ac009a798ba8b2f6d6dccda785032ecc99786130a6616149ddcd4253f9c28
Stable URL of this page
https://metraipolis.com/documento/dc_fc89d0eba8e2

How to cite

WeaveData: A Multimodal Data Analysis System with Self-Critiquing and Self-Evolving LLM Plans — arXiv:2609.34764 — arXiv (en), https://arxiv.org/abs/2609.34764 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc89d0eba8e2 (Metraipolis archive dc_fc89d0eba8e2, sha256 c34ac009a798ba8b2f6d6dccda785032ecc99786130a6616149ddcd4253f9c28)
BibTeX
@misc{dcfc89d0eba8e2,
  title = {WeaveData: A Multimodal Data Analysis System with Self-Critiquing and Self-Evolving LLM Plans — arXiv:2609.34764},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34764},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc89d0eba8e2; sha256 c34ac009a798ba8b2f6d6dccda785032ecc99786130a6616149ddcd4253f9c28},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34764. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal data analysis, which answers questions over relational tables, text, and images, has attracted growing attention in the data management community. Large language models (LLMs) enable such analysis in natural language by generating analysis plans over relational and semantic operators. However, LLM-generated plans are error-prone: a plan may silently compute something other than what was asked, fail during execution, or return a result that misses the question. This paper presents WeaveData, a multimodal data analysis system with self-critiquing and self-evolving LLM plans. First, WeaveData generates a typed logical plan for each question and critiques it step by step before execution, and it checks the executed result against the question afterwards. Second, WeaveData evolves a plan that fails or misses the question: it diagnoses the failure with the actual data, reuses the results that remain valid, and accumulates planning experience for later questions. Third, WeaveData grounds planning in a metadata knowledge graph of all modalities, clarifies ambiguous questions with the user, and backs every model judgment with evidence in an interactive notebook. We demonstrate WeaveData on two public multimodal datasets.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Databases (cs.DB) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.34764 — 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 2026-10-07T20:29:03.152Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).