Metraipolis › archive › dc_7649f0247488

SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning — arXiv:2608.14452

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14452
License (as archived)
CC0-1.0
Archived
2026-10-19T02:20:50.262Z
SHA-256 of the archived text
1a71e8882d198269ab762fa96d3c848e7d19b4e2e6a5654f243c21283eee23e1
Stable URL of this page
https://metraipolis.com/documento/dc_7649f0247488

How to cite

SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning — arXiv:2608.14452 — arXiv (en), https://arxiv.org/abs/2608.14452 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7649f0247488 (Metraipolis archive dc_7649f0247488, sha256 1a71e8882d198269ab762fa96d3c848e7d19b4e2e6a5654f243c21283eee23e1)
BibTeX
@misc{dc7649f0247488,
  title = {SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning — arXiv:2608.14452},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14452},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7649f0247488; sha256 1a71e8882d198269ab762fa96d3c848e7d19b4e2e6a5654f243c21283eee23e1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14452. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Spreadsheets are widely used to organize, analyze, and manipulate semi-structured data, yet automated spreadsheet reasoning remains challenging for large language models (LLMs). Real-world workbooks often contain implicit cross-table associations, fine-grained column dependencies, and complex spatial layouts. Existing methods typically flatten these multidimensional structures into sequential strings, losing important intra-sheet boundaries and inter-sheet semantics. Consequently, LLMs cannot exploit the global spatial context that human experts naturally use when inspecting spreadsheets. We propose SheetCompass, a graph-guided and memory-driven agentic framework for spreadsheet reasoning and automation. SheetCompass explicitly models structural relationships within and across worksheets while maintaining task-relevant information in memory, enabling agents to reason more effectively over complex workbooks.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.14452 — 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 2026-10-19T02:02:02.824Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).