Metraipolis › archive › dc_697a0b160e64
Toward Effective and Reliable LLM Agents via Dynamic Ontology — arXiv:2608.22974
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.22974
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:41:45.054Z
- SHA-256 of the archived text
098a80afd58ff5fbc33ef7b392c56907fb5e3c9a7344b41d84b8b73fb66e75bb- Stable URL of this page
https://metraipolis.com/documento/dc_697a0b160e64
How to cite
Toward Effective and Reliable LLM Agents via Dynamic Ontology — arXiv:2608.22974 — arXiv (en), https://arxiv.org/abs/2608.22974 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_697a0b160e64 (Metraipolis archive dc_697a0b160e64, sha256 098a80afd58ff5fbc33ef7b392c56907fb5e3c9a7344b41d84b8b73fb66e75bb)
BibTeX
@misc{dc697a0b160e64,
title = {Toward Effective and Reliable LLM Agents via Dynamic Ontology — arXiv:2608.22974},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.22974},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_697a0b160e64; sha256 098a80afd58ff5fbc33ef7b392c56907fb5e3c9a7344b41d84b8b73fb66e75bb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22974. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model (LLM) agents rely heavily on knowledge encoded in model parameters or presented as unstructured context. In domain-specific tasks, this leaves important semantic connections implicit. This often results in incomplete evidence use and brittle multi-step decisions. Ontologies offer a way to externalize domain concepts and relations as machine-interpretable structures, but constructing task-usable ontologies traditionally requires substantial effort from domain experts and is difficult to scale. Automatic construction is also challenging: an ontology that appears semantically plausible may not contain the relational structures needed for actual decision making. We present OaK, an ontology-as-a-kernel framework that dynamically constructs and refines task-oriented ontologies for LLM agents. Given task requirements and training data, OaK constructs an ontology and its knowledge graph, generates task-adaptation functions for graph reasoning, and uses judge feedback to iteratively refine both. By making relevant concepts and relations explicit, the ontology grounds knowledge retrieval and multi-step decision making. We evaluate OaK on TravelPlanner, CRMArenaPro, and ToolQA. Results show that OaK improves standard LLM agents, strengthens evidence grounding, and boosts the reliability of multi-step reasoning. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.22974 — 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 2026-10-18T07:37:52.755Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).