Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 10 papers 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.
Using FIBS to train white-box probes to monitor agent sabotage behavior and undisclosed deception
Published Oct 9
Evaluated models Qwen3.5-397B-A17B , Qwen3.5-122B-A10B , Qwen3.5-27B and others10 提出基于决策前隐藏状态的检测与引导，预测并抑制智能体欺骗
Published Oct 5
Evaluated models Qwen3-14B Abstract 论文展示了智能体自发欺骗可在行为显现前由内部表征预测，并通过激活引导证实了表征的行为可操作性。
提出 Control OSWorld，评测失准 GUI Agent 的监控
Published Oct 2
Evaluated models Claude Sonnet 4.6 , Claude Opus 4.8 , GPT-5.2 and others6 提出 Auto Mode ++，加固编码 Agent 阻断监视器
Published Sep 17
Evaluated models Opus 5 , Opus 4.8 , Opus 4.7 and others8 Abstract 系统评估生产阻断监视器在面对持续恶意智能体时的表现，提出加固防御并指明多上下文防御挑战。
用成对比较奖励与假阳性校准训练对齐审计模型
Published Aug 26
Evaluated models Claude Haiku 4.5 , Llama 3.3 70B , DeepSeek v3.1 and others4 Abstract 系统总结了强化学习训练对齐审计器的核心问题、成对奖励与校准方法及主要结果。
评测开发者能否在协作编程中发现编码 Agent 的隐蔽破坏
Published Jun 4
Evaluated models Claude-Opus-4.6 , GPT-5.4 , Gemini-3.1-Pro and others5 提出 Gram 审计框架，测量编程与研究智能体的破坏倾向
Published May 29
Evaluated models Gemini 2.5 Pro , Gemini 3.0 Pro Preview , Gemini 3.1 Pro Preview 构建 SLEIGHT-Bench 评测代码智能体监控对概念盲点规避的捕获
Published May 16
Evaluated models Claude Opus 4.6 , Claude Opus 4.7 , Claude Sonnet 4.6 and others6 Abstract 评估针对监控盲点的规避基准，发现前沿监控器漏报率高，算力与脚手架虽有提升但存在类别局限。
提出 Meerkat，聚类并搜索 Agent 轨迹库以定位跨轨迹安全违规
Published Apr 14
Evaluated models GPT-5.4 , GPT-5.4-mini , Qwen3.5-397B-A17B and others5 Abstract Meerkat 用聚类与智能体搜索定位跨轨迹违规，并在真实评测轨迹中找出脚手架泄题与奖励黑客。Meerkat 是事后审计方法，用来在智能体轨迹仓库里找出单条看不出、合在一起才违反自然语言安全属性的见证。
提出针对可信监控器的自适应提示注入，绕过 AI 控制协议
Published Oct 10, 2025
Evaluated models GPT-4o , GPT-4 , GPT-4.1 and others4 Abstract 作者指出当前依赖 LLM 监控器的 AI 控制协议易被自适应提示注入攻破，呼吁引入多监控器集成与数据流隔离机制。
You have reached the end