Probabilistic Orchestrator for Indeterministic Multi-Agent Systems in Real-Time Environments
Algorithms · 29.03.2026 · 19 (4) · 261
DOI: 10.3390/a19040261 ↗Kurz gefasst
Fachartikel in der Zeitschrift Algorithms, online erschienen am 29.03.2026. Verfasst von Arkady Bovshover und 2 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Multi-agent perception systems must operate under fundamental asymmetries: some agents provide fast but unreliable observations, while others deliver higher-quality evidence with delay and uncertain correspondence. Traditional deterministic orchestration and rule-based fusion struggle to manage these trade-offs, often producing brittle or unstable behavior. We introduce a probabilistic orchestration framework that treats coordination as an epistemic generation problem—constructing and updating belief states under uncertainty—rather than a selection problem. Instead of committing to a single agent’s output, the orchestrator constructs a belief state that explicitly represents uncertainty, evidential provenance, and temporal relevance. Decisions are produced through latency-aware, association-weighted fusion, and uncertainty itself becomes a first-class signal governing action, deferral, and learning. Crucially, the orchestrator enables controlled teacher–student adaptation: high-confidence, well-associated stationary observations are gated into a feedback loop that improves ego perception over time while mitigating error amplification. We demonstrate the approach on an infrastructure-assisted dual-camera obstacle-recognition task. Experimental results show improved robustness to distance, occlusion, and delayed evidence compared to ego-only and deterministic orchestration baselines. By operationalizing orchestration as epistemic generation, this work provides a unifying framework for robust decision-making and safe adaptation in multi-agent systems, with implications that extend beyond perception to agentic and generative AI architectures.
Zitieren
APA
Bovshover, A., Kojukhov, A., & Levin, I. (2026). Probabilistic Orchestrator for Indeterministic Multi-Agent Systems in Real-Time Environments. Algorithms, 19(4), 261. https://doi.org/10.3390/a19040261
Vancouver
Bovshover A, Kojukhov A, Levin I. Probabilistic Orchestrator for Indeterministic Multi-Agent Systems in Real-Time Environments. Algorithms. 2026;19(4):261. doi:10.3390/a19040261
BibTeX
@article{Bovshover2026,
author = {Bovshover, Arkady and Kojukhov, Andrei and Levin, Ilya},
title = {Probabilistic Orchestrator for Indeterministic Multi-Agent Systems in Real-Time Environments},
journal = {Algorithms},
year = {2026},
volume = {19},
number = {4},
pages = {261},
doi = {10.3390/a19040261}
}
EUVIMED