In agentic systems, human-generated data records anchor the value of AI services. However, cloud compute pipelines centralize processing on remote servers, leading to data centralization, which reduces personal data sovereignty and may degrade the quality of service (QoS). Meanwhile, user contributions are diverse in quantity and quality: decentralized records can be biased, noisy, and heterogeneously distributed.
To address the data challenge, we study fair token allocation and private data valuation for decentralized and resource-constrained agentic systems. Our approach embeds multi-modal representations in a shared semantic space and releases differentially private (DP) prototypes to preserve utility while reducing semantic leakage. With the DP guarantee, we design a fair token allocation scheme that rewards effective contributions and remains robust to data heterogeneity and AI resource scarcity.
Extensive simulations demonstrate improved contribution-based fairness and QoS compared to standard benchmarks. The improved resistance to image reconstruction attacks indicates enhanced privacy for multi-modal personal data.
Blogger's Review: This paper addresses the critical issues of fairness and privacy in multi-modal agentic systems. The proposed token allocation mechanism not only enhances service quality but also effectively protects user privacy, making it highly valuable for practical applications and research significance.