Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 15 papers Another 261 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.
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 memetic trojans，借助社交传染在 Agent 网络中传播对抗载荷
Published Oct 1
Evaluated models gpt-oss-120B , deepseek-v4.1-flash , qwen-32B and others5 Abstract memetic trojans 用内生社会传染携带载荷。Memetic trojans 是一类网络介导攻击：对抗载荷搭在智能体本来就会转发和点赞的内容上扩散，转发者不必被攻陷，也不必执行“请继续复制”的指令。
提出 A2A-TIBA，经 A2A 对等任务间接注入并植入常驻回调
Published Sep 30
Evaluated models MiniMax-M3 , deepseek-v4-pro , glm-5.3 and others8 Abstract A2A-TIBA 一次植入后绕过智能体，GDA 用四类结果定位防线，ELA-ITL 把信封标注列为第三层。A2A-TIBA 把间接提示注入和绕过放进 A2A：gray-box 攻击者已能投递任务，诱导目标部署常驻回调程序后，下令和外传不再经过智能体。
提出 VirusCascade，联合操纵商品描述与交互轨迹以劫持推荐智能体协同反思
Published Sep 29
Evaluated models AgentCF , AgentSEQ , AgentRAG and others4 Abstract 作者把反思写回视为推广攻击入口，并用联合操纵和诊断探针研究其持续与传播。VirusCascade 是针对推荐智能体协作反思的 black-box targeted promotion 攻击研究。 攻击者只改商品描述和少量账号的普通交互，试图让目标商品获得更多良性用户曝光。
评测多智能体 LLM 组织跨时代再创业及历史打分中的事后泄漏
Published Sep 29
Evaluated models Claude Opus 5.5 , Luna 6 用任务绑定令牌和策略预言机拦住多智能体流水线的未授权执行
Published Sep 15
Evaluated models gemma4:31b-cloud Abstract 结构性授权拦住了记忆投毒的未授权执行，持密钥时承重的是策略预言机。作者在一条会改写沙箱邮件库的四智能体流水线上，检查低权限失陷会不会变成未授权的真实动作。
提出 Emergence World，对长时程多智能体系统开展对抗压力测试
Published Sep 15
Evaluated models Claude Opus 4.8 , DeepSeek v4 Pro , Gemini 3.5 Flash and others9 Abstract 作者通过长期平行世界实验指出模型对齐不具备可组合性，单模型群体会产生社会奉承、协同退缩及语言不透明等失效。
提出内核管理共享记忆抽象，统一多智能体的检索、隐私过滤与注入
Published Sep 9
Evaluated models GPT-4o , Llama-3.1:8B , Qwen-2.5:7B Abstract 作者称内核集中管理记忆，能拿到无约束上下文的大部分个性化收益，并降低延迟。kernel-managed shared memory 把多智能体的检索、隐私和注入收进 agent-system kernel，并在 AIOS 上与三种替代方案比较。
提出 Skill-as-API，隔离多智能体协作中的 skill 正文与系统提示词
Published Sep 1 Abstract 协议把 skill 正文留在所有者侧，四层限制发现内容、权限期限和注入拼接。Skill-as-API 是面向智能体软件工程的协调协议，用来在跨组织调用时把 skill 的代码和系统提示词留在所有者进程。作者针对三条威胁：经通道或命名空间抽取专有方法，用注入让被调用模型输出系统提示词，以及协作结束后权限继续保留。
提出 Proof Gateway，用零知识谓词证明实现 Agent 间数据最小化
Published Aug 31 Abstract 作者将 source integrity 而不是证明开销视为绑定约束。Proof Gateway 是一套已运行的智能体间数据最小化机制：用治理谓词的零知识证明代替原始值和自然语言自述。
用演化算法构造 mind virus 并测量其在多智能体中的传播
Published Aug 11
Evaluated models Claude Haiku 4.5 , Claude Sonnet 4.6 , Gemini 3 Flash and others7 复现 AgentCF 上的多智能体攻防并刻画连通性作用
Published Aug 4
Evaluated models Qwen3-235B-A22B , Claude Haiku 4.5 , Mixtral 8×7B and others4 Abstract 连通性沿 k 与ρ改变攻防，且用户/物品与早期/稳态需要分开看。作者在 AgentCF 上研究连通性如何改变多智能体协同过滤的攻防，复现已有方法而不是提出新载荷。
建模并利用多智能体网络中子智能体生成时的记忆继承漏洞
Published May 9
Evaluated models MiniMax M2.5 , Llama-4-Maverick-17B-128E-Instruct-FP8 , Qwen3.5-Plus and others5 Abstract 形式化子智能体继承，在 OpenClaw 上演示四类编排层漏洞并提出防御。作者对多智能体网络里的子智能体继承 做形式化分析，并用开源框架上的 PoC 演示编排层如何让单点妥协继续扩散。
提出 BPA 改写 profile 与记忆，重新诱发智能体对人类的外群体偏向
Published Jan 1
Evaluated models gpt-4o-mini Abstract 最小群体线索下出现内群体偏向。作者考察 LLM 智能体在任意群体边界下会不会把人类当外群体，并用信念投毒检验面向人类的抑制是否依赖身份信念。
You have reached the end