
Supplementary materials for the survey paper LLM-Based Multi-Agent Orchestration: A Survey of Frameworks, Communication Protocols, and Emerging Patterns by Y. Zhu and F. Toffoletto, to appear in Future Internet (MDPI, 2026), Special Issue "Generative AI: Systems, Technologies and Applications". Contents: prisma_screening.csv — per-stage PRISMA-style screening log (identification → screening → eligibility → included). prisma_databases.csv — the six databases and exact query strings searched during the literature review. references_rating.csv — per-reference evidence-tier rating for all 80 bibliography entries (peer-reviewed / preprint / standards / vendor-reported / industry-survey / regulatory). orchestration_decision_tree.json — machine-readable serialization of the Section 4.5 decision framework for orchestration-pattern selection. orchestration_decision_tree.md — prose walkthrough with ASCII and Mermaid renderings of the decision tree (Figure 7 of the paper). README.md — bundle overview and evidence-tier mapping. DATA_AVAILABILITY_STATEMENT.md — the exact Data Availability Statement that appears in the paper. LICENSE — full CC-BY-4.0 license text.
Generated for the MDPI Future Internet submission. No new empirical data; this bundle aggregates screening logs, reference-level evidence-tier ratings, and the machine-readable decision framework derived from Section 4.5 of the paper.
CrewAI, Model Context Protocol, LangGraph, communication protocols, agent orchestration, large language models, survey, multi-agent systems, Agent-to-Agent, AutoGen
CrewAI, Model Context Protocol, LangGraph, communication protocols, agent orchestration, large language models, survey, multi-agent systems, Agent-to-Agent, AutoGen
| 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 |
