# DMind-3: A Sovereign Edge--Local--Cloud AI System with Controlled Deliberation and Correction-Based Tuning for Safe, Low-Latency Transaction Execution

arXiv: https://arxiv.org/abs/2602.11651 · HTML: https://mlsanity.com/paper/2602.11651/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 69 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents](https://mlsanity.com/paper/2410.02644/) (2024)
- [A Survey of Model Compression and Acceleration for Deep Neural Networks](https://mlsanity.com/paper/1710.09282/) (2017)
- [CrypTen: Secure Multi-Party Computation Meets Machine Learning](https://mlsanity.com/paper/2109.00984/) (2021)
- [HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection](https://mlsanity.com/paper/2409.17504/) (2024)
- [Securify: Practical Security Analysis of Smart Contracts](https://mlsanity.com/paper/1806.01143/) (2018)
- [Security and Privacy on Blockchain](https://mlsanity.com/paper/1903.07602/) (2019)
- [A Survey on Ethereum Systems Security: Vulnerabilities, Attacks and Defenses](https://mlsanity.com/paper/1908.04507/) (2019)
- [A Survey of Smart Contract Formal Specification and Verification](https://mlsanity.com/paper/2008.02712/) (2020)
- [SoK: Transparent Dishonesty: front-running attacks on Blockchain](https://mlsanity.com/paper/1902.05164/) (2019)
- [Attacking the DeFi Ecosystem with Flash Loans for Fun and Profit](https://mlsanity.com/paper/2003.03810/) (2020)
- [Frontrunner Jones and the Raiders of the Dark Forest: An Empirical Study of Frontrunning on the Ethereum Blockchain](https://mlsanity.com/paper/2102.03347/) (2021)
- [A Survey on Security and Privacy Issues of Bitcoin](https://mlsanity.com/paper/1706.00916/) (2017)
- [A Flash(bot) in the Pan: Measuring Maximal Extractable Value in Private Pools](https://mlsanity.com/paper/2206.04185/) (2022)

## Abstract (arXiv)

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 (C3-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.