EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Ethical Coordination of LLM Multi-Agent Systems

J. de Curtò, I. de Zarzà, Carlos T. Calafate

Electronics · 25.05.2026 · 15 (11) · 2278

DOI: 10.3390/electronics15112278 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 25.05.2026. Verfasst von J. de Curtò und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: LUXEMBOURG Institute of Science and Technology, BARCELONA Supercomputing Center.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Embedding large language model (LLM) coordinators in production electronic systems, connected vehicles, multi-robot fabrics, IoT control loops, telecommunications orchestration, demands a pre-delivery filter stage that preserves ethical guarantees under adversarial influence at deployment scale. We present a constitutional governance layer that filters compiled influence policies before they reach a heterogeneous population of grounded LLM agents whose hybrid decision model combines a game-theoretic base probability with an LLM-evaluated narrative shift attenuated by per-agent resistance. Four experiments on a Barabási–Albert scale-free network of 30 agents powered by Llama-3.3-70B-Instruct show that the filter holds an Ethical Cooperation Score (ECS) of 0.176 (multi-seed mean 0.163, 95% confidence interval (CI) [0.150,0.174]) against an unconstrained baseline of ECS=0, enforced by a hard integrity gate (1.000 vs. 0.000). We surface an autonomy paradox in which unconstrained agents resist manipulation more forcefully (0.856 vs. 0.728) yet collapse to ECS=0, establishing that system-level integrity cannot be delegated to agent-level defence. The advantage is monotonic in resistance (+0.174 to +0.183), seed-stable (Cliff’s δ=1.0, complete separation), topology- and backbone-invariant across five contemporary LLMs, robust to alternative ECS formulations, and reproduces at N = 100. Against constitutional artificial intelligence (CAI) critique-revise and LlamaGuard-style safety-classifier baselines, the framework matches the integrity floor and adds a measurable margin on the secondary risk surface (burst timing, composite manipulation risk). The filter runs at 0.78 μs/call (≈1.3×106 decisions/s/core), supporting always-on deployment as a stateless, model-agnostic component of LLM agent pipelines in adversarially contested electronic systems.

Förderung

  • LUXEMBOURG Institute of Science and Technology
  • BARCELONA Supercomputing Center

Zitieren

APA

Curtò, J. D., Zarzà, I. D., & Calafate, C. T. (2026). Ethical Coordination of LLM Multi-Agent Systems. Electronics, 15(11), 2278. https://doi.org/10.3390/electronics15112278

Vancouver

Curtò JD, Zarzà ID, Calafate CT. Ethical Coordination of LLM Multi-Agent Systems. Electronics. 2026;15(11):2278. doi:10.3390/electronics15112278

BibTeX
@article{Curt2026,
  author = {Curtò, J. de and Zarzà, I. de and Calafate, Carlos T.},
  title = {Ethical Coordination of LLM Multi-Agent Systems},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {11},
  pages = {2278},
  doi = {10.3390/electronics15112278}
}
Kostenlos starten →