Random access (RA) is one of the most foundational medium access control (MAC) layer scheduling schemes for handling unpredictable data traffic from multiple terminals. While multi-agent reinforcement learning (MARL) has been explored to optimize RA-based wireless networks, its reliance on experience-driven, distribute...
Scientific artificial intelligence (AI), spanning foundation models (FMs) to federated data-analysis pipelines, is becoming shared infrastructure across national laboratories, universities, hospitals, and industrial partners. This collaboration creates privacy risks whose natural unit is often an institution's particip...
O. Kotevska, Sumit Kumar Jha, A. Bellet et al.· 1 citation
Multi-agent LLM systems can improve reasoning by pooling diverse perspectives, but their effectiveness depends on coordinating communication, particularly in hidden-profile settings where each agent holds only part of the evidence required for a correct decision. Existing protocols, including fixed schedules, round-rob...
Abhijith Babu, Ramneet Kaur, Vishal Pramanik et al.· 0 citations
An autonomous cyber defender trained with reinforcement learning (RL) is typically tied to the network on which it was trained, limiting its ability to generalize as network scale changes. Hierarchical RL reduces decision complexity by separating strategic targeting from tactical execution, but it does not eliminate th...
Harshith Doppalapudi, Nathaniel D. Bastian, Ankit Shah· 0 citations
Autonomous red team agents increasingly stress-test AI-enabled cyber defenses by planning strategy and executing multistage attacks. Reinforcement learning (RL) and large language models (LLMs) offer complementary mechanisms for the planning and execution such agents require, and prior work has combined them in hybrid...
A. Shaikh, Arunesh Sinha, Nathaniel D. Bastian et al.· 0 citations
A trust-aware monitor is developed that combines probabilistic localization trust, calibrated using real GPS spoofing data, with behavioral evidence from task execution to classify agents and remove detected adversaries from subsequent planning.
R. Francos, Daniel Garces, Orhan Eren Akgün et al.· 0 citations
This work is the first to establish the finite-time convergence for achieving lower-level second-order stationary solutions in general LLNC-BLO and proposes the PROBE (Perturbed gradient algorithm for bilevel problem), which achieves a finite-time convergence rate of O(T^{-2/5}) where T denotes iterations.
Zhi-Yao Zhang, Meng-Lu Yu, Alvaro Velasquez et al.· 0 citations
This work introduces MeshHeal, a fully decentralized self-healing framework that couples ability-matched peer review across two timescales and introduces Model-Backed MAS Evaluation, which ties ability assignments to execution models, since prompt-based ability assignments alone can leave routing errors hidden.
Ke-Ru Chen, Sen-Fon Lin, Ying-Bin Liang et al.· 0 citations
Network Feasibility Geometry Reinforcement Learning (NFG-RL) is proposed, which models coupled constraints via transport theory and the residual inclusion of $\bphi_{\mathfrak{N}}(x,a)\in\cK_{\mathfrak{N}}$, defining the executed policy as the pushforward of a proto-policy through a feasibility-transport map.
Zu-Yuan Zhang, Ze-Yu Fang, Mahdi Imani et al.· 0 citations
Mixed human-AI teams often operate with limited explicit communication under task uncertainty, so effective coordination requires quickly identifying which latent task or environment model best explains the observed interaction. This paper develops implicit task-hypothesis inference, enabling an AI agent to maintain a...
A. Ravari, Seyede Fatemeh Ghoreishi, Nathaniel D. Bastian et al.· Conference on Control Techno...· 0 citations
CUSP (Collective Uncertainty through Semantic Opinion Pooling), a training-free uncertainty quantification framework that maps multiple VLM responses to a shared semantic response space, pools them into a pooled semantic opinion, and reports two complementary system-level signals.
C. Yu, David Garcia, Brian Jalaian et al.· 0 citations
Across CIFAR10, COIL100, and ETH80 under FGSM and Genetic Attack, ViT + Classical HDC degrades more gracefully than Pure HDC and ViT + HDC baselines, and achieves higher normalized AURC, lower attack-time decision margins, and larger gains from partial adversarial retraining.
Hamza Errahmouni Barkam, Salaar Saraj, Zhen Ye et al.· International Symposium on L...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
