Metraipolis › archive › dc_c456ffbc6fbe

An Agentic Framework Using Rules and LLMs for Embedding and Annotating Descriptive Document Layouts: A Plant Science Use Case — arXiv:2608.14587

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.14587
License (as archived): CC0-1.0
Archived: 2026-10-18T17:02:07.970Z
SHA-256 of the archived text: 4cc33699829a6b9fab44b940289a90f19bef4a6ba20953cc830f1fa9c3d70006
Stable URL of this page: https://metraipolis.com/documento/dc_c456ffbc6fbe

How to cite

An Agentic Framework Using Rules and LLMs for Embedding and Annotating Descriptive Document Layouts: A Plant Science Use Case — arXiv:2608.14587 — arXiv (en), https://arxiv.org/abs/2608.14587 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c456ffbc6fbe (Metraipolis archive dc_c456ffbc6fbe, sha256 4cc33699829a6b9fab44b940289a90f19bef4a6ba20953cc830f1fa9c3d70006)

BibTeX

@misc{dcc456ffbc6fbe,
  title = {An Agentic Framework Using Rules and LLMs for Embedding and Annotating Descriptive Document Layouts: A Plant Science Use Case — arXiv:2608.14587},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14587},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c456ffbc6fbe; sha256 4cc33699829a6b9fab44b940289a90f19bef4a6ba20953cc830f1fa9c3d70006},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14587. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Background: Recent advances in information retrieval (IR) leverage both dense and sparse representations, large language models (LLMs), and specialized retrieval models to improve ranking accuracy, relevance, and cross-lingual performance. Complementary techniques such as passage indexing, document layout analysis, and semantic knowledge representation further enhance retrieval effectiveness by capturing fine-grained contextual and structural information. Emerging agentic LLM frameworks extend these capabilities by enabling planning, iterative reasoning, tool use, and multi-agent collaboration, thereby broadening applications across diverse domains. These frameworks also emphasize rigorous evaluation, ethical considerations, and trustworthiness, ensuring responsible deployment in real-world settings. We propose a modular, agent-based pipeline for botanical trait extraction. Optical character recognition (OCR) converts PDFs into machine-readable text, while segmentation and indexing organize content by genus and species. Rule-based parsers extract structured botanical traits, and ensembles of large language models (LLMs) expand trait vocabularies and resolve ambiguities. This approach ensures accurate species recognition, scalable annotation, and explainable integration of textual botanical descriptions, enabling robust and interpretable data extraction across large botanical corpora. Results: Using three regional botanical datasets, our system extracted 55,737 trait annotations across 4,961 species, averaging 9.1 traits per species. Integration of LLM-based enrichment improved coverage for 75% of traits, increasing total annotations by 59%. While the choice of OCR engine had a minor effect on species recognition, overall annotation counts remained stable, demonstrating the robustness, scalability, and reliability of the pipeline for large-scale botanical trait extraction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.14587 — 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 2026-10-18T16:29:13.707Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).