Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 117 papers Another 262 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.
Show that reward hacking can propagate through code, memory, and plans in multi-agent coding systems
Published Oct 9
Evaluated models Qwen2.5-Coder-14B , Gemma-3-12B , Qwen2.5-Coder-7B and others16 Abstract The authors state that reward hacking can spread across models and affect routing and aggregation, and that review can reduce delivery.Reward hacking induced by coding RL can leave the source agent and enter subsequent collaboration and system coordination.
Measures citation fragility in AI search, demonstrating that ordinary public posts can enter citations and answers.
Published Oct 8
Evaluated models Grok , Doubao , ChatGPT and others10 Abstract The authors claim the paper quantifies vulnerabilities in AI search caused by citation preferences and low posting thresholds; tests show public web posts can penetrate AI citations, and they call for auditing the citation supply chain.
提出流匹配逆向框架，从多向量视觉文档索引重构页面
Published Oct 7
Evaluated models Tomoro-ColQwen3-8B , ColQwen3.5-4.5B , Tomoro-colqwen3-embed-4b and others13 提出 agent plasticity 指标衡量智能体通过经验自我改进的效率
Published Oct 7
Evaluated models Claude Fable 5 , Claude Opus 5 , GPT-5.6 Sol and others10 Abstract 作者用固定权重协议比较前沿模型把经验写成制品后的留出增益与习得效率。作者用 agent plasticity 衡量一件事：权重冻结时，智能体把经验写成可继承制品，再换成留出能力增益，这个转换有多省。
提出 RAG-PIBench，评测 RAG 上下文中提示注入检测器
Published Oct 6
Evaluated models DistilBERT-base-uncased , DeBERTa-v3-base , MiniLM 用 Learn2Play Bench 评测 Agent 从经验中学习陌生规则
Published Oct 6
Evaluated models Claude Opus 5.5 , GPT-6 Astra , Claude Opus 5 and others11 Abstract 用隐藏规则游戏把新学习与预训练知识分开，并比较模型、记忆方式和人类。Learn2Play Bench 用新设计的隐藏规则文本游戏，评测 LLM 智能体在不更新权重时从交互中学习的能力。
提出 DAEDALUS，用自生成任务自举 Agent 记忆
Published Oct 6
Evaluated models GPT-5.4-mini , GPT-5.6 Luna , Qwen3.6-35B-A3B and others11 实现 DEFER，以确定性检查优先拦截多智能体流水线的内容攻击
Published Oct 6
Evaluated models Qwen3-235B-A22B-Instruct-2507 , gpt-oss-120b , Llama-4-Scout-17B-16E-Instruct and others5 Abstract DEFER 把确定性检查放在 judge 之前。DEFER 用来测量多智能体授权流水线里，确定性规则在何处结束、LLM judge 从何处开始。
提出 SkillPoison，用局部有效的成功经验诱导自进化 Agent 形成过度泛化技能
Published Oct 6
Evaluated models deepseek-v4-flash , Qwen V3.8 Flash , GPT-5.5 Abstract SkillPoison 通过局部有效且验证成功的经验诱导技能过度泛化，在多个评测基准上实现了持久的下游攻击影响。SkillPoison 提出了一种针对自进化智能体经验到技能形成过程的攻击范式，通过组织已验证的成功经验诱导技能过度泛化。
评测记忆门控对激活诱导与记忆诱导谄媚的防御效果
Published Oct 6
Evaluated models Llama-3.1-8B-Instruct , Qwen2.5-7B-Instruct , Mistral-7B-Instruct-v0.3 and others4 Abstract 作者称外部记忆过滤成立，数据未显示反向转向再有贡献。作者在四个开源指令模型上，把激活转向和外部记忆处理放进同一纵深防御协议，看记忆诱发谄媚和内部谄媚压力能否分开压低，以及个性化效用还剩多少。要处理的问题是：检索到的用户历史会推动模型顺从存储信念。只改外部上下文，并不直接动模型内部的谄媚表征。
提出检索可采纳性核验框架，评测记忆智能体的记录资格与披露
Published Oct 6
Evaluated models DeepSeek V4 Pro , Gemini 3.6 Flash , GPT-5.6 Luna and others7 Abstract 作者用三值可采纳性和匹配召回界审计长时记忆检索，并分开报告支持、资格与披露。这是一套长时记忆检索的可采纳性核验协议，用来分开检查候选支持、资格、提示词暴露和答案披露，而不是提出新的检索算法。 。
提出 SAFESHIELD，组织小语言模型部署时的安全决策
Published Oct 6
Evaluated models Qwen3-4B-Instruct Abstract SAFESHIELD 用可审计决策轨迹组织 SLM 部署时的四项安全决策，并报告协调依赖影响端到端结果。SAFESHIELD 是面向小语言模型的部署时安全框架，把运行时安全从单项审核改写成可检查的决策过程。
提出 AMU 按推导图门控企业 Agent 共享记忆的列级访问
Published Oct 6 Abstract 在完整血缘下，AMU 按列权限放行缓存，并标出同名 KPI 冲突。AMU 用列级推导门控共享记忆，拦截经缓存流出的无权敏感列，并标出同名 KPI 的定义冲突。
提出临时可见性协议，限制持续摄入 RAG 向量库的投毒暴露
Published Oct 5 Abstract 用截止期限制未核验可见时长。这篇工作给持续摄入的 RAG 向量库一个失败关闭的临时可见性协议，把协议能限制的未核验暴露和依赖检测器的中毒暴露分开。
构建 AGENTDOXX 基准，评测联网搜索 Agent 对匿名访谈的再识别
Published Oct 5
Evaluated models GPT-5.6 Terra , GPT-5 Mini , GPT-4.1 Mini and others10 Abstract 论文提出了已知身份的重识别基准 AGENTDOXX，揭示搜索与记忆双重风险及现有防御在检索轨迹中的泄露漏洞。
提出 StateWise，在编码智能体行动前诊断并修复失效持久状态
Published Oct 4
Evaluated models GPT-5.6-sol , DeepSeek v4 Pro , Qwen 3.7 Max and others4 Abstract StateWise 在动作前修复失效的持久前提。StateWise 是在执行带副作用的动作之前，诊断并修复编码智能体持久操作状态的框架。
提出 MemAdapter，在检索后约束记忆对智能体推理的影响
Published Oct 4
Evaluated models DeepSeek-V4-Flash , GPT-5.6-sol , Qwen3-8B Abstract 检索后三阶段调节记忆角色。MemAdapter 是给长期记忆智能体用的检索后调节框架，用来处理记忆诱发谄媚。
测量事实核查评测混入的时序证据与参数泄漏
Published Oct 4
Evaluated models Qwen3-14B , phi-4 Abstract 两条后见通道会抬高事实核查分数。作者量的是 LLM 事实核查分数里，有多少来自 claim 当时还不可知的信息。通道有两条：预训练记住的结局，以及检索到的、写于 claim 之后的文档。
提出 RAGStress 受控基准，评测知识库退化下的 RAG
Published Oct 4
Evaluated models Claude Sonnet 4 , Claude Opus 4.6 , DeepSeek R1 and others5 Abstract 作者用 RAGStress 比较五系统。RAGStress 是知识库损坏下的 RAG 受控压力测试。作者明确不把它当作模型排行榜。
提出 StegoMemory，评测智能体持久记忆作为跨会话隐写信道
Published Oct 3
Evaluated models Llama 3.1 405B , Claude 3.5 Sonnet , GPT-4o and others13 Abstract 研究揭示智能体持久记忆可作为隐蔽信道跨会话传输机密，写入持久化是主要防御瓶颈，呼吁建立记忆完整性防御。