Towards Scenario-Driven Reference Architecture for Integrating Microservices and LLM-Based Multi-Agent Systems
Bibliographic record
Abstract
Microservice Systems (MS) and Large Language Model-based Multi-Agent Systems (LLM-MAS) are two major paradigms shaping modern software design. While MS emphasizes modularity and scalability, LLM-MAS introduces adaptive reasoning and autonomy. However, deriving systematic insights into their similarities, differences, and integration potential remains challenging due to their complex heterogeneous technology stacks. This poster proposes a scenario-driven methodology as the core analytical approach. By grounding the comparison of MS and LLM-MAS in concrete, domain-specific scenarios within the retail supply chain management, we expose architectural contrasts and connections across both paradigms. Using this case study, we demonstrate how scenario-driven analysis captures functional workflows, architectural constraints, and quality attributes, enabling the derivation of a layered reference architecture. This provides a structured base for hybrid integration and the development of scenario-based evaluation benchmarks, including failure injection aligned with the SOTA taxonomy.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".