Translation in progress Some entries still include text in the original language.
Oct 13 · Tuesday
All papers Found 31 papers Another 215 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.
Proposes a local dual-model closed loop to generate edge scenarios for autonomous system safety assurance
Published Oct 9
Evaluated models PPO Abstract Local closed-loop generation of JSON edge cases.The authors built a local agentic loop that runs on a laptop to generate edge cases for safety arguments of autonomous systems, rather than releasing a new public test set.
Proposes EndoRSI, recursively improving endoscopic robot policies with physical evidence
Published Oct 9
Evaluated models Qwen3-VL-4B A survey of risks, defenses, and evaluation in the six-stage lifecycle of world models
Published Oct 9 Abstract Safety is written as a property of the prediction-decision closed loop; claims must be linked to observed consequences and versions.World model safety is organized by the nature of the prediction-decision loop, not by isolated prediction scores.
Proposes the FAITH safe filtering reinforcement learning framework, training high-dimensional systems to optimize task reward under constraints
Published Oct 9 Abstract FAITH separates safety filtering from reward optimization.FAITH is a model-free safe filtering reinforcement learning framework for high-dimensional systems: safety correction and task reward reside in separate modules.
Propose COAP, which uses stateful code to control a robot at test time without a model
Published Oct 9 提出 SOUL 稀疏特征策略遗忘，缓解 VLA 状态幻觉
Published Oct 7
Evaluated models OpenVLA , π0.5 Abstract SOUL 以稀疏特征遗忘 VLA 状态幻觉。SOUL 用稀疏特征引导的策略 unlearning 处理 VLA 的 state hallucination。
提出 VeriFine，用双环协同扩展验证以实现具身推理自我改进
Published Oct 7
Evaluated models Alpamayo 1.5 8B , Qwen3-VL 2B , Claude Opus 5 Abstract VeriFine 用双环协同演化具身推理的策略、课程和评审，驾驶与导航的策略分和评审对齐都上升。VeriFine 把驾驶和导航推理的自改进写成策略、课程和无参考评审的协同演化，用来处理固定评审跟不上新失败模式的问题。
提出 Inspect Robots，在真实机器人上评测具身模型的能力与拒答
Published Oct 5
Evaluated models Astra（GPT-6 Astra） , GPT-6 Sol , GPT-5.6 Sol and others7 提出 Perturbot 扰动训练，打破 VLA 的模态捷径
Published Oct 3
Evaluated models π0.5 Abstract Perturbot 改训练数据以削弱三类模态捷径，GroundFscore 用来看成功是否来自任务证据。Perturbot 是一套不改推理的 VLA 训练期数据干预，用来削弱模态捷径，并用离线分数区分“任务变好”和“靠捷径变好”。
提出 CrashSim 用真实事故先验引导扩散仿真并构建 nuCrash 评测自动驾驶规划器
Published Oct 3
Evaluated models Lane-graph planner , PDM-closed planner , IL planner and others5 Abstract CrashSim 迁入真实事故先验生成场景。CrashSim 用检索到的真实事故先验引导扩散式多车仿真，为自动驾驶安全评测生成碰撞与近碰撞场景。 。
论证人形机器人学习四层代理可在目标缺失时报成功
Published Oct 2
Evaluated models Gaussian MLP（三隐层各 128 ELU，独立 critic，PPO） Abstract 四层都可能在目标缺失时报告成功。作者讨论腿式机器人 RL 流水线中，奖励、课程门控、评测统计量和参考运动如何在物理目标缺失时仍报告成功。传统观点只把奖励当作会被优化、因而会偏离的代理。
提出 SceneFactory-3D，用路况反事实评测驾驶策略的闭环安全性
Published Oct 2
Evaluated models Frozen L0 , L0-T , L1 and others5 Abstract SceneFactory-3D 固定场景只改路况。SceneFactory-3D 是 GPU 批处理的多智能体驾驶仿真器，用来在场景和控制器固定时只改路面物理，并比较闭环结果。
审计机器人安全监控的细化缺口，比较表面计划与图细化轨迹的裁决
Published Oct 2 Abstract 表面轨迹可漏掉图诱导的禁区进入。作者审计 RoboGuard 的一个假设：对高层动作轨迹的安全裁决，在补上语义图诱导的导航和已记录隐式效应之后是否仍然成立。做法是不改验证器，并固定同一条 LTL。
提出 FAIL BANK，用运行时 CBF 反馈自进化更新 VLA 策略
Published Sep 30
Evaluated models π0.5 , π0 提出 DrivingBench，评测通用视觉语言模型能否闭环驾驶真车
Published Sep 30
Evaluated models GPT-6 Astra , Claude Fable 5.1 , Grok 4.6 and others4 Abstract 仅 Astra 第二次跑完低速锥桶路线。DrivingBench 评测通用 VLM 能否自己闭环开真车，推理延迟也算进任务。
提出 QPT，用奖励与成本 Q 惩罚训练满足约束的离线强化学习策略
Published Sep 28 Abstract QPT 把条件 Transformer 与奖励/成本 Q 惩罚连成训练–推理一致的安全离线 RL 方法。QPT 针对安全离线 RL：只从离线数据学习，同时处理约束满足、回报最大化和行为正则，并希望部署时更换成本阈值而无需重训。
提出 PHIRL，用进度标注对齐逆强化学习奖励
Published Sep 26
Evaluated models PHIRL , PHIRL-online Abstract PHIRL 用进度四维对齐 AIRL 奖励。PHIRL 用进度标注修正从示范反推的奖励，以减少真人在环，同时不把示范中的每一步都当成任务进展。
提出 NAVSAFE-∞ 写真闭环基准，评测端到端驾驶策略的闭环安全
Published Sep 22
Evaluated models LTF , DiffusionDrive , DrivoR and others13 Abstract 写真事件级闭环基准显示开环高分不能稳定变成闭环安全。NAVSAFE-∞ 用写真、事件级闭环仿真检查端到端驾驶策略的安全，而不是只看开环轨迹分数。
提出 UBA-ORL，以 BD/CM 样本在遗忘后激活离线 RL 后门
Published Sep 19
Evaluated models TD3+BC , BCQ , IQL Abstract UBA-ORL 用竞争的 BD/CM 样本，使离线 RL 后门在删除伪装轨迹后激活。UBA-ORL 研究离线强化学习中由合规轨迹删除激活的后门：合法贡献者同时上传共享触发的后门轨迹和伪装轨迹，训练后触发响应被压低，删除伪装批次后再升高。受害系统是使用静态数据集和轨迹级遗忘接口的离线 RL 服务。对手不能看到训练算法、参数、梯度或具体遗忘算法，但能提交可区分批次，并在部署时向观测注入预定触发。
提出 DriveMCP 框架，将感知、交规检索与车辆遥测接成可审计驾驶辅助层
Published Sep 15 Abstract DriveMCP 用可审计专家工具和 RSS/TTC 仲裁做驾驶辅助，作者称违章与超速低于三个 VLM 基线。DriveMCP 是面向高级驾驶辅助的模块化智能体框架，把感知、合规、车辆状态和安全仲裁拆开并留下审计轨迹。