An official website of the United States government
This paper introduces a trust-aware task allocation framework for adversarial multi-agent systems, leveraging quantum optimization to improve decision-making under uncertainty. The approach models agent reliability and adversarial behavior through a trust-aware utility function, enabling robust and adaptive task assignment in dynamic environments. By incorporating quantum-inspired optimization techniques, the framework efficiently explores complex solution spaces that are difficult for classical methods. Experimental results demonstrate improved resilience to adversarial agents, enhanced allocation efficiency, and overall system robustness compared to baseline approaches. The proposed framework contributes to secure and scalable coordination in distributed systems, with applications in cybersecurity, autonomous systems, and networked sensing environments.
more »
« less
This content will become publicly available on March 17, 2027
Resilience in Ambient Multi-Agent LLMs via Decentralized Bio-Autonomic Control and Immune-Inspired Anomaly Detection
Large Language Model (LLM) agents are now widely deployed in Ambient Intelligence (AmI) environments, where autonomous agents must sense, act, and coordinate at scale. As agent capabilities and interdependence increase, traditional reliability strategies such as isolated adaptive control, anomaly detection, or trust modeling have proven inadequate due to their fragmented and scenario-specific nature. Comprehensive architectures that enable integrated self-management, collective anomaly response, robust information dissemination, and privacy-preserving adaptation remain scarce. We propose a bio-autonomic framework for decentralized resilience in multi-agent LLM systems where a unified architecture systematically applies principles from biological autonomic systems to LLM-based multi-agent environments. Specifically, each agent implements an autonomic control loop, formally structured as Monitor-Analyze-Plan-Execute over a shared Knowledge base (MAPE-K), for self-regulation. At the system level, the framework integrates immune-inspired anomaly detection using the Dendritic Cell Algorithm, probabilistic computational trust, decentralized gossip for robust information sharing, and federated learning with homomorphic encryption for collaborative, privacy-preserving adaptation. This holistic approach enables LLM agent ecosystems to self-organize, detect and isolate faults, and collectively adapt as system complexity increases. Empirical evaluations show that our framework achieves substantially improved resilience and recovery compared to state-of-the-art multi-agent baselines.
more »
« less
- Award ID(s):
- 2046435
- PAR ID:
- 10676636
- Publisher / Repository:
- Proceedings of the AAAI Conference on Artificial Intelligence
- Date Published:
- Journal Name:
- Proceedings of the AAAI Conference on Artificial Intelligence
- Volume:
- 40
- Issue:
- 44
- ISSN:
- 2159-5399
- Page Range / eLocation ID:
- 37332 to 37340
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Multi-user environments present significant challenges in coordinating diverse preferences and resolving conflicts around shared resources. Current systems use a single-agent approach that struggles to balance individual needs with collective objectives. We introduce MALLM, a novel framework that deploys personalized LLM-based agents for each user on edge devices. MALLM integrates multi-sensor data fusion with a structured multi-agent decision-making mechanism, processing all data locally for enhanced privacy. Our edge-computing architecture enables real-time deliberation through evidence-based argumentation and consensus formation algorithms. The system continuously refines user profiles through sensor data while managing computational resources e!ciently. We evaluate MALLM through two case studies-health monitoring and personalized comfort management- demonstrating improved conflict resolution and resource e!ciency compared to conventional approaches. Our results show that MALLM e''ectively balances competing user priorities while preserving privacy in complex shared environments.more » « less
-
In multi-agent systems, dynamic average consensus (DAC) is a decentralized estimation strategy in which a set of agents tracks the average of time-varying reference signals. Because DAC requires exchanging state information with neighbors, attackers may gain access to these states and infer private information. In this paper, we develop a privacy-preserving method that protects each agent’s reference signal from external eavesdroppers and honest-but-curious agents while achieving the same convergence accuracy and convergence rate as conventional DAC. Our approach masks the reference signals by having each agent draw a random real number for each neighbor, exchanges that number over an encrypted channel at the initialization, and computes a masking value to form a masked reference. Then the agents run the conventional DAC algorithm using the masked references. Convergence and privacy analyses show that the proposed algorithm matches the convergence properties of conventional DAC while preserving the privacy of the reference signals. Numerical simulations validate the effectiveness of the proposed privacy-preserving DAC algorithm.more » « less
-
The rise of mobile multi-agent robotic platforms is outpacing control paradigms for tasks that require operating in complex, realistic environments. To leverage inertial, energetic, and cost bene fits of small-scale robots, critical future applications may depend on coordinating large numbers of agents with minimal onboard sensing and communication resources. In this article, we present the perspective that adaptive and resilient autonomous control of swarms of minimal agents might follow from a direct analogy with the neural circuits of spatial cognition in rodents. We focus on spatial neurons such as place cells found in the hippocampus. Two major emergent hippocampal phenomena, self-stabilizing attractor maps and temporal organization by shared oscillations, reveal theoretical solutions for decentralized self-organization and distributed communication in the brain. We consider that autonomous swarms of minimal agents with low-bandwidth communication are analogous to brain circuits of oscillatory neurons with spike-based propagation of information. The resulting notion of `neural swarm control' has the potential to be scalable, adaptive to dynamic environments, and resilient to communication failures and agent attrition. We illustrate a path toward extending this analogy into multi-agent systems applications and discuss implications for advances in decentralized swarm control.more » « less
-
The increasing adoption of smart home devices has raised significant concerns regarding privacy, security, and vulnerability to cyber threats. This study addresses these challenges by presenting a federated learning framework enhanced with blockchain technology to detect intrusions in smart home environments. The proposed approach combines knowledge distillation and transfer learning to support heterogeneous IoT devices with varying computational capacities, ensuring efficient local training without compromising privacy. Blockchain technology is integrated to provide decentralized, tamper-resistant access control through Role-Based Access Control (RBAC), allowing only authenticated devices to participate in the federated learning process. This combination ensures data confidentiality, system integrity, and trust among devices. This framework’s performance was evaluated using the N-BaIoT dataset, showcasing its ability to detect anomalies caused by botnets such as Mirai and BASHLITE across diverse IoT devices. Results demonstrate significant improvements in intrusion detection accuracy, particularly for resource-constrained devices, while maintaining privacy and adaptability in dynamic smart home environments. These findings highlight the potential of this blockchain-enhanced federated learning system to offer a scalable, robust, and privacy-preserving solution for securing smart homes against evolving threats.more » « less
