1
Diffuse AI Control on Fuzzy Tasks
聚焦AI安全中的“弥散威胁”，探讨大模型在长期部署中可能出现的对齐漏洞与风险控制方法。
arXiv:2606.08892v1 Announce Type: new Abstract: AI models deployed in critical domains, such as AI safety research, may subtly sabotage our efforts du…
2
Your AI Trading Agent Will Lose All Your Money — Here's How To Stop It
直击AI交易代理的致命缺陷，99%的代理都会亏钱——关键在于防止安全剧场，构建不可妥协的架构组件。
Your AI Trading Agent Will Lose All Your Money — Here's How To Stop It I want you to imagine waking up, grabbing your phone, and seeing a flood of not…
3
Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs
新方法保障LLM在线部署每轮风险可控，基于共形预测与RLVR训练，安全认证更可靠。
arXiv:2605.20270v1 Announce Type: new Abstract: A local specialist LLM, fine-tuned with reinforcement learning from verifiable rewards (RLVR) on opera…
4
Conformal Thinking: Risk Control for Reasoning on a Compute Budget
将推理预算设定问题重构为风险控制问题，在限制错误率的同时最小化计算量，用分布自由的方法自适应控制推理何时停下，既省Token又保精准。
arXiv:2602.03814v2 Announce Type: replace Abstract: Reasoning Large Language Models (LLMs) enable test-time scaling, with dataset-level accuracy impro…