Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 254 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.
提出只训练或篡改多智能体潜在通信链路来提高有害遵从
Published Sep 30
Evaluated models Llama-3.2-3B-Instruct , Qwen2.5-3B-Instruct , Gemma-3-1B-IT and others7 Abstract 潜在链路本身即可改变冻结智能体系统的安全，奖励既能攻击也能修复。学习得到的潜在通信链路会改变由冻结、对齐智能体组成的系统是否遵从有害请求。 。作者研究三种拓扑：双智能体、三级顺序协作，以及双专家加汇总。
提出 MADBench，评测多智能体辩论是吸收还是放大对抗影响
Published Sep 30
Evaluated models gpt-4o , GPT-5 , GPT-6 Astra Abstract MADBench 显示辩论能吸收部分准确率攻击，同时放大未授权读写。MADBench 是一个评测多智能体辩论安全性的基准，用来看攻击是被辩论吸收还是被放大。
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。
提出双控多智能体基准 DUMA-Bench，测量对抗环境下的策略违反
Published Sep 21
Evaluated models GPT-5 , GPT-5-mini , GPT-5-nano and others14 Abstract DUMA-Bench 用双控交互评测智能体安全。DUMA-Bench 把 τ²-bench 的双控交互做成智能体安全评测，用来看策略违反如何随用户、模型和环境一起出现。
提出多智能体系统提示注入的威胁模型与四层架构防御
Published Sep 19
Evaluated models GPT-4o (2024-08-06) , Claude 3.5 Sonnet , Llama 3 70B-Instruct 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。
提出谱系图治理层抑制多智能体协作的错误级联
Published Mar 4 Abstract 单一种子可沿固定协作图固化为错误共识。作者把 LLM-MAS 中“小错变成集体错误共识”做成图上的可测传播，并用只改消息、不改拓扑的插件压低最终感染。
提出多轮在线骚扰 Agent 基准，评测记忆、规划与微调越狱
Published Oct 16, 2025
Evaluated models LLaMA-3.1-8B-Instruct , Qwen3-30B-A3B-Instruct , DeepSeekMoE-16B and others4 You have reached the end