Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 305 papers do not have category tags yet and are not included in filtered results.
“
About this collection Collection in progress We are building a large AI safety paper collection to help researchers find work related to their interests. Papers are collected automatically andfiltered only for relevance to AI safety , without judging quality, novelty or reading value. The default “Annotated first” shows papers with tags or published paper analyses first. Each group is ordered by original publication date, newest first, with undated papers last. “Newest first” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and paper analyses are prepared by AI from the papers. Language models may have systematic biases and produce hallucinations.We plan to carry out human annotation and review to reduce errors in this content.
提出 AI Agent 主张的可审计性框架与裁决规则
Published Oct 6 Abstract 主张须事先固定四要素。作者给出把关于已部署智能体的主张写成可核查陈述的条件,而不是检测器或攻击方法。
提出 statepoint 运行时,一致回滚并分支 Agent 的本地与远程状态
Published Sep 28 Abstract statepoint 支持回滚与分支。Planarian 是与现有 harness 协同的运行时,把智能体环境收成可恢复、可分支的时间点。
作者提出 Issuer-Sovereign Agentic Payments,由发卡行决定是否生成认证值。论文无实验。
Published Sep 23 Abstract 发卡行按已批规则决定是否生成认证值,支付仍走原有卡通道。Issuer-Sovereign Agentic Payments 把智能体消费限额留在发卡行认证步骤里,而不是在扣款时依赖银行外的 credential provider。
提议前沿开发者托管嵌入式评估,审查内部智能体监控、权限与对齐
Published Sep 22 Abstract 论文建议前沿开发者现在就以接近员工的现场访问,持续审查内部监控、权限与对齐。嵌入式评估 是一种第三方评估:独立评估者在前沿 AI 开发者现场获得接近员工的系统、人员与文档访问,用来审查依赖内部系统与实践的风险。
提出弹性沙箱基础设施 DSec,支撑大规模智能体训练
Published Sep 19 Abstract DSec 是面向大规模智能体 RL 的多后端生产沙箱,用分层、按需镜像和训练协同维持高密度。DSec 是 DeepSeek-AI 的生产沙箱平台,用来支撑从 DeepSeek V3.2 到 V4.1 的智能体 RL 与评测,而不是报告某个模型的任务准确率。
综述工具调用 Agent 的授权架构,提出主体层级与结构要求
Published Sep 15 Abstract 叙事综述用主体层级把工具调用授权收成七项要求,并标出强制与聚合两处缺口。这是一篇关于工具调用型智能体授权架构的结构化叙事综述,分析单位是每一次使模型之外系统产生效果的调用。
提出结合 Scientist AI 监督与系统级控制的智能体保障架构
Published Sep 9 Abstract 作者梳理事件中的多层失效,主张监督模型、系统控制与证据治理并用。Lu 与 Bengio 给出的是一套可逐层上移的保障架构和一组事件归类,不是已测量的防御系统。
提出多智能体输出与跨部署方委派的两层存证
Published Aug 31 Abstract 两层证明记录放出字节与边授权。部署方侧的两层证明,用来在多智能体跨部署方委托之后回答两个事后问题:谁放出了这些字节,这条跨部署方边有没有父方授权。
You have reached the end