DMind-3: A Sovereign Edge--Local--Cloud AI System with Controlled Deliberation and Correction-Based Tuning for Safe, Low-Latency Transaction Execution
This addresses the need for safe, low-latency transaction execution in Web3 for users and developers, though it appears incremental by combining existing edge, local, and cloud approaches with novel training objectives.
The paper tackles the problem of securing irreversible financial execution in Web3 environments against adversarial risks and strict latency constraints by introducing DMind-3, a sovereign Edge-Local-Cloud AI system, which achieves a 93.7% multi-turn success rate in protocol-constrained tasks and superior domain reasoning compared to general-purpose baselines.
This paper introduces DMind-3, a sovereign Edge-Local-Cloud intelligence stack designed to secure irreversible financial execution in Web3 environments against adversarial risks and strict latency constraints. While existing cloud-centric assistants compromise privacy and fail under network congestion, and purely local solutions lack global ecosystem context, DMind-3 resolves these tensions by decomposing capability into three cooperating layers: a deterministic signing-time intent firewall at the edge, a private high-fidelity reasoning engine on user hardware, and a policy-governed global context synthesizer in the cloud. We propose policy-driven selective offloading to route computation based on privacy sensitivity and uncertainty, supported by two novel training objectives: Hierarchical Predictive Synthesis (HPS) for fusing time-varying macro signals, and Contrastive Chain-of-Correction Supervised Fine-Tuning (C$^3$-SFT) to enhance local verification reliability. Extensive evaluations demonstrate that DMind-3 achieves a 93.7% multi-turn success rate in protocol-constrained tasks and superior domain reasoning compared to general-purpose baselines, providing a scalable framework where safety is bound to the edge execution primitive while maintaining sovereignty over sensitive user intent.