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.
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.
提出 IEC 与 IntAct，测量并修复 Agent 工具调用的路径篡改
Published Oct 3
Evaluated models qwen3-coder-plus , Qwen2.5-Coder-32B , Qwen2.5-72B and others4 Abstract 论文界定工具调用在执行路径中的意图偏离问题，提出无执行归因协议与跳级修复，为智能体工程提供评测与设计准则。
提出 STAR-Guard 双层防御，抑制长程 Agent 遗忘跨轮安全约束
Published Oct 2
Evaluated models GPT-5.5 , DeepSeek-V4-Pro , GLM-5.2 and others7 Abstract 揭示 GHOST 跨轮约束遗忘风险，构建 SCARBench 基准并通过 STAR-Guard 双层防御消除违规。
提出 AuraForge，从漏洞修复合成安全测试并训练编码 Agent
Published Oct 1
Evaluated models Qwen3.5-4B , GLM 4.7 Flash , Qwen3-Coder-Next and others7 Abstract AuraForge 用攻击效果测试和防泄露环境做成 AuraGym，合成监督的误拒更低，训出的 4B 模型增益高于人工测试。AuraForge 把真实仓库的历史漏洞修复变成可执行训练任务，用来监督编程智能体同时满足功能请求和隐含的安全要求。
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 提出契约约束的工具调用修复协议，在执行前拦截非法补丁
Published Sep 29
Evaluated models 2B rank-8 LoRA , 0.8B rank-4 LoRA 提出 IntentFlux 测量 Agent 意图漂移并提出 StateForge 修复
Published Sep 26
Evaluated models Claude Opus 4.7 , DeepSeek V4 Pro , Gemini 3.5 Flash and others9 Abstract INTENTFLUX 量化意图漂移，STATEFORGE 用显式状态部分缩小差距，但未回到单轮水平。这篇工作把“用户改口后，过时意图仍影响答案或工具动作”做成可评分的多轮失败，并试验在生成前显式维护活跃状态。
提出 VILTA，在闭环训练中用 VLM 编辑邻车轨迹以提升驾驶策略鲁棒性
Published Jan 19 Abstract VILTA 在闭环中编辑邻车轨迹以训练驾驶策略。VILTA 是一个把视觉语言模型放进自动驾驶闭环训练的框架，用来应对长尾危险场景不足。
You have reached the end