
This dataset accompanies the master's thesis "Towards an Ontology of Normative Role Design for LLM Agent Interactions in Multi-Agent Systems," submitted to the Erasmus Mundus Joint Master's Programme in Artificial Intelligence for Sustainable Societies (AISS) at Tallinn University. The deposit contains two files: Ontology_Normative_Role_Design_LLM_MAS.xlsx — A multi-tab spreadsheet encoding the ontology developed in this thesis. It includes per-paper coding sheets for 38 studies, a master synthesis sheet aggregating coded dimensions (role design, domain, outcomes, failures), and a triples sheet formalising the ontology as entity–relation–entity triples (515 triples, 212 entities, 15 relation types). SLR_Screening_Sheet.xlsx — The systematic literature review screening log documenting the full pipeline from approximately 700 initial records to the 38 studies included in the final analysis, with inclusion/exclusion decisions and criteria.
multi-agent systems, large language models, role design, ontology, systematic literature review, normative design, LLM agents, system prompts
multi-agent systems, large language models, role design, ontology, systematic literature review, normative design, LLM agents, system prompts
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
