Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 261 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.
Proposing DRYLAB-Bench to evaluate agentic LLMs' high-risk mutation design capability
Published Oct 9
Evaluated models Claude Opus 5 , Claude Opus 4.8 , Claude Fable 5 and others15 提出 RSIGym 环境,评测研究智能体的递归自改进
Published Oct 8
Evaluated models Claude Opus 5 , Claude Opus 5.5 , GPT-6 Astra and others9 提出 TasteVal 基准,衡量模型设计实验并解释结果的研究品味
Published Oct 6
Evaluated models Opus 5.5 , Fable 5.1 , GPT-6 Astra and others20 评测 Agent 选择并早期操作高风险生物工具的能力
Published Oct 3
Evaluated models Claude Opus 4.7 , Gemini 3.1 Pro Preview , GPT-5.5 and others7 Abstract 七模型能选工具并部分操作 EVEscape 与 ESM3。这项评估测量七个前沿 LLM 智能体与生物工具交互的最早两步:为设计任务选工具,以及在仓库里完成玩具级操作。作者关心的是,有生命科学背景但不会专门操作高风险工具的行为者,能否借此降低门槛。范围限于预测性、生成性工具。
用 CyberPersistBench 评测入侵后安装与持久化能力
Published Sep 29
Evaluated models GPT-5.6-sol , Claude Sonnet 5 , DeepSeek-V4-pro and others5 Abstract CyberPersistBench 将入侵后持久化拆成可核验阶段,并比较原生防御与多主机条件。CyberPersistBench 是评测入侵后安装与持久化的基准,关注初始访问消失后是否仍能维持原生立足点。 。
Published Sep 9
Evaluated models GPT-5.4 , Claude Sonnet 4.6 , GPT-4.1 and others6 用 VirtualCrime 沙盒评测模型被赋予犯罪角色后的多步执行与过度伤害
Published Jan 20
Evaluated models GPT-4.1 , GPT-5 , Claude-Haiku-4.5 and others8 Abstract 作者称八个 LLM 会在沙盒中编排多步犯罪,手段偏欺骗与协作,并出现过度伤害。VirtualCrime 是一个多 LLM 智能体的文本沙盒,用来测量模型在被指定犯罪目标之后的多步行为,而不是测量它会不会拒绝恶意查询,也不是测量它会不会自发产生恶意意图。作者要回答的是:初始防护被角色指派绕过之后,模型在会调查、报警并逮捕队伍的环境里,能规划并执行什么,以及执行时是否超出任务所需去使用武力或破坏。除这一指派外,不用外部工具或任务特定脚手架。
You have reached the end