Model based approach to detect emergent behavior in multi-agent systems
Bibliographic record
Abstract
Multi-agent systems (MAS) are efficient solutions for commercial applications such as robotics, business commerce applications, information retrieval and search engines. In MAS, agents are usually designed with distribution of functionality and control. Lack of central control implies that the quality of service of MAS may be degraded because of possible unwanted behavior at runtime, commonly known as emergent behavior. Detecting and removing emergent behavior during the design phase of MAS will lead to huge savings in deployment costs of such systems. Effective and efficient design validation of MAS requires the development of systematic and automated methodologies to review MAS design documents. Although the increasing demand for MAS in the software industry has led to the development of several Agent Oriented Software Engineering (AOSE) methodologies, the AOSE methodologies usually do not fully cover monitoring and testing. In this paper, a technique to help MAS developers verify, test and monitor MAS design is introduced. This method uses MAS analysis and design artifacts created by the MaSE AOSE methodology. In this technique, design artifacts of MaSE are converted to scenario-based specification, which is very similar to UML's sequence diagrams. Then the specifications are used to analyze the system for validating the design of MAS and ensuring the lack of emergent behavior.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".