Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 29 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.
提出义务识别基准 ObligationBench，并训练护栏识别 Agent 未履行的安全义务
Published Oct 8
Evaluated models ObligationGuard , Claude-Opus-4.8 , GPT-5.6-Sol and others17 Abstract 义务是护栏缺口。作者认为编码智能体的安全不能只靠拦截禁止动作，还要找出终止时仍未做的安全关键动作，并将其称为义务。
提出 PyCache Trap，用字节码缓存替换绕过 Agent 技能扫描器
Published Oct 7
Evaluated models CISCO , HSS , AUDITOR and others8 Abstract 论文剖析智能体技能审查与执行脱节盲区，提出 PyCache Trap 攻击并构建基于可信复现的 EAV 防御。这篇论文研究了智能体技能（Agent Skills）安全扫描中的“审查–执行脱节”问题，并提出了对应的攻击验证与防御方案。
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。
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 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。
提出检测、结构化与 GSPO 流程，降低共识生成的提示注入错位
Published Oct 3
Evaluated models LLaMA-2 7B , LLaMA-3 8B , GPT 3.5 Turbo and others14 Abstract 三章依次做个体偏好预测、政党知识图谱审议，以及共识生成对提示注入的脆弱性与一条防御流程。这是一篇把 LLM 数字孪生放进增强民主的博士论文，分个体表示、政党聚合和共识生成的提示注入三章。
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 提出 SkillDRE，用预执行与运行时双阶段反馈演化恶意 Agent 技能
Published Sep 26
Evaluated models DeepSeek-V4-Pro , GLM-5.2 , Qwen3.5-397B-A17B and others4 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 PMPA，经外部源向 Agent 持久记忆投毒并跨会话泄露隐私
Published Sep 12
Evaluated models DeepSeek-V4-Flash , DeepSeek-V4-Pro , Qwen3-Max Abstract 论文提出了持久记忆投毒攻击 PMPA，报告了 harness 智能体在处理外部数据时易受跨会话记忆投毒与隐私泄露的风险。
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 CS-Guard 基准，评测代码生成护栏对虚构场景攻击的防御
Published Sep 9
Evaluated models CodeLlama-13B-Instruct , DeepSeekCoder-V2-Lite-16B , GPT-OSS-20B and others7 Abstract 论文提出了代码安全护栏基准 CS-Guard，评估发现现有护栏对虚构场景攻击和代码级恶意请求防御较弱。
提出针对 Agent Harness 的上下文特权提升攻击
Published Sep 1
Evaluated models GPT-5.5 , GPT-5.4 mini , Claude-Sonnet-4.6 and others7 提出 SkillMisevo-Bench，量化自改进 Agent 的技能误演化
Published Aug 13
Evaluated models Claude Code , Codex , Hermes and others4 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 提出 ColluSkill，用跨技能组合绕过 Agent 技能扫描器
Published Aug 10
Evaluated models GPT-5.5 , DeepSeek-V4-Pro , GLM-5.2 Abstract 论文揭示了单技能孤立扫描的盲区，提出多技能链攻击 ColluSkill 与上下文防御 ChainGuard 并验证了有效性。
构建 ContextWeave，评测办公工作流智能体记忆的下游增益
Published Aug 5
Evaluated models DeepSeek-V4-Pro , GPT-5.5 , GLM-5.1 and others5 Abstract ContextWeave 用真实办公任务流检验记忆是否改善工作区质量与偏好对齐。ContextWeave 是面向语言智能体记忆的纵向基准，用来看召回先前经验能否让后续办公任务做得更好。