基于人类编写本体论，实现LLM代理的可证明安全与可审计性，为智能体可靠性提供新路径。
arXiv:2606.04903v1 Announce Type: cross Abstract: We introduce the LLM agent architecture Agentic Redux, intended for use with nontrivial problem doma…
新研究用可证明方式保护微调大模型免遭训练数据窃取，同时维持模型效能，隐私与实用兼得。
arXiv:2602.00688v2 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) on sensitive datasets raises privacy concerns, as trainin…
首次证明带接口约束的工作流学习能保证收敛，理论突破为自动化流程生成奠基。
arXiv:2605.19140v1 Announce Type: new Abstract: We study workflow learning in a setting where specialized agents hand off control through a shared art…
深度神经网络公平性修复新突破，提供可证明保证，已被ASE 2025录用。
arXiv:2605.19549v1 Announce Type: cross Abstract: Deep neural networks (DNNs) are suffering from ethical issues such as individual discrimination. In …
后量子时代多智能体AI治理系统，提出可证明安全的MAGIQ架构，解决新兴计算范式下的安全挑战。
arXiv:2605.06933v2 Announce Type: replace Abstract: Our computing ecosystem is being transformed by two emerging paradigms: the increased deployment o…