Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 265 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 评估自动化 AI 研发触发智能爆炸的可能并提出政策应对
Published Sep 29 Abstract 软件驱动智能爆炸可能把数年进展压进数月，作者要求三项政策先做好。Chan 等论证：自动化 AI 研发可能经软件反馈环形成智能爆炸，把本需数年的进展压进数月或更短。他们关心的不是换硬件的建设周期，而是 AI 扩大有效研发劳动力、再产出更强系统，以及社会能否在能力跃迁前看见、约束并适应这一过程。
提出双层系统 AIDE2，使研究智能体自改进 Harness 并对比人类研发基线
Published Sep 22
Evaluated models gemini 3 flash , gpt-5.6-sol , fable 5 Abstract 提出双层递归自改进系统 AIDE2，在固定预算下演化 Harness 代码，多项留出基准超越人类基线并降低奖励黑客。
提出影子评测，衡量 Agent 自主完成开放式 AI 科研的能力
Published Jul 30
Evaluated models Claude Opus 4.8 , GPT-5.6 Sol , GPT-5.3 Codex Abstract 论文通过影子评测发现前沿智能体能独立胜任科研工程实现，但在科学探索与有效利用反馈上未达到顶会门槛。
构建 SciHazard 基准，评测科研智能体与 LLM 的科学危险能力
Published Jul 21
Evaluated models WebThinker + DeepSeek-R1 , InternAgent , Gemini Deep Research and others19 Abstract SciHazard 用分解评分测科学滥用风险，作者称智能体抬高了可执行危害。SciHazard 是一个科学滥用风险基准，配一个把危害拆开再合成的自动分数。
提出 SciTrace，为科学发现智能体加入跨阶段安全推理与工具轨迹核验
Published Jun 6
Evaluated models Llama-3.1-70B-Instruct , Qwen2.5-72B-Instruct , DeepSeek-V3 and others4 Abstract SciTrace 把安全推理织入科学智能体各阶段，在 SciSafetyBench 上提高安全指标并保持输出质量。SciTrace 是加在科学发现智能体流水线上的安全框架，不是再在各阶段出口放一个独立过滤器。
Abstract 作者主张防护优先于自主性，用三元框架把输出安全扩展到行为与环境反馈。这是一篇关于 LLM 驱动 AI scientists 的 perspective：自主科研能力增强时，误用和意外后果缺少科学情境下的系统防护。
You have reached the end