Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 200 papers Another 255 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 RSI-Anything, which uses a world model to select candidates and retain policy updates.
Published Oct 10
Evaluated models ReasonFlux-Coder-7B , 4B policy , W1 Abstract RSI-Anything integrates world models into recursive self-improvement through prediction, feedback, and retention checks, and reports gains across multiple domains.RSI-Anything is a cross-domain framework: it uses world model predictions to decide which candidates to take external feedback for, then uses the feedback to decide whether the policy, workflow, or predictor is updated, and uses checks to decide which pair is retained. The difficulty to address is the limited interaction budget, and the fact that once the policy changes, the candidate distribution faced by the predictor also changes. The authors argue that improving only one side does not guarantee that the assembled system will be better.
Proposing DRYLAB-Bench to evaluate agentic LLMs' high-risk mutation design capability
Published Oct 9
Evaluated models Claude Opus 5 , Claude Opus 4.8 , Claude Fable 5 and others15 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.
Proposes SWE-Duel, which lets coding agents mutually evaluate, create problems, and blindly review fixes during evaluation.
Published Oct 9
Evaluated models GPT-5.5 , Claude Opus 4.8 , Kimi K2.7 Code and others11 Abstract The mutual evaluation arena creates questions during evaluation.SWE-Duel is a coding agent arena that generates tasks and judges only at evaluation time, to avoid leakage and saturation of static benchmarks.
Extending reinforcement learning for full-modality foundation models to support agent self-improvement
Published Oct 8
Evaluated models MiMo-V2.6-Pro , MiMo-V2.6-Flash , MiMo-V2.6-Distill-Qwen-9B Abstract The series uses three-dimensional RL and group scoring to improve agent scores; the authors claim the final performance is comparable to frontier models.MiMo-V2.6 is an all-modality MoE technical report, pursuing agent self-improvement by scaling up RL computation, environments, and scoring.
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。
提出研究合同，把已批准选择绑定到执行证据并由检查器核验
Published Oct 8
Evaluated models OpenAI gpt-5.6-sol , OpenAI gpt-5.6-terra , OpenAI gpt-5.6-luna and others18 Abstract 研究合同暴露四类输出单独建不立的关系。研究合同用来核验计算科学研究智能体是否仍在已批准研究之内，不判断科学是否为真。 。
重建 Agent 技能复制网络并建模源选择以指导安全审计
Published Oct 8 Abstract 论文重构了 GitHub 智能体技能复制网络，发现复制集中于少数仓库且很少随源更新，并提出了代码库审计推荐模型。
提出 RSIGym 环境，评测研究智能体的递归自改进
Published Oct 8
Evaluated models Claude Opus 5 , Claude Opus 5.5 , GPT-6 Astra and others9 用对照实验隔离评测设计对漏洞补丁基准得分的影响
Published Oct 7
Evaluated models Claude Sonnet 4.0 , Claude Sonnet 4.5 , Claude Opus 4.7 Abstract 作者认为评测流水线会改变补丁基准分数，PoC 通过率高于开发者测试通过率。作者把 LLM 漏洞补丁基准的评测流水线当作会改变测量结果的对象，并明确说本文不是再做一个用于排名的基准。
提出 comprehension audits，以人类理解证据作为继续研发门槛
Published Oct 7 Abstract 理解审计把出示人类理解设为继续研发的门禁，并报告开源评审评论率下降。本文是一份研发过程保障提案：用 comprehension audits 检验责任人是否理解 AI 参与产生的研发贡献，未达标就暂停后续开发与依赖该贡献的发布。 。
提出 AgentTime 基准，评测智能体按时长工作与估时能力
Published Oct 7
Evaluated models Fable 5.1 , GPT-5.6 Sol , GPT-6 Astra and others7 Abstract 作者把完成任务和管理所用时间分开。AgentTime 是对智能体时间自控的评测：预测任务耗时、按要求时长工作、事后估计已用时间。
提出 TESTJACK，动态审计编码基准通过判定是否满足任务要求
Published Oct 7
Evaluated models Claude Opus 4.6 , Claude Opus 4.7 , Claude Opus 4.8 and others7 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 Secure-CUA，用动作事务约束计算机使用智能体的不可信影响
Published Oct 7
Evaluated models Claude Opus 5 , Gemini 3.8 Flash , GPT-5.6-Sol Abstract Secure-CUA 用每步事务约束不可信影响，良性 TSR 接近 Vanilla-CUA。Secure-CUA 要限制图形界面里不可信内容对 CUA 决策和 GUI 执行的影响，同时保留合法任务所需的不可信信息。
提出 PackHallu，经规则文件提示注入诱导编码 Agent 换用攻击者指定包
Published Oct 7
Evaluated models Qwen2.5-Coder-7B , Qwen3-Coder-30B , Devstral-Small-2-24B and others19 Abstract PackHallu 诱导规则文件换包。PackHallu 研究一种针对编程智能体规则文件的提示注入：让智能体在本应使用合法依赖时，改导入攻击者指定并控制的包。
提出 WebMirage，用局部对抗图像劫持视觉网页 Agent 的浏览器操作
Published Oct 7
Evaluated models LLaVA-v1.5-13B , LLaVA-v1.6-34B , MiniCPM-o-8B and others6 Abstract 论文提出了针对网络智能体的端到端视觉红队框架 WebMirage，揭示了从视觉定位到浏览器执行的安全脆弱性。WebMirage 是一个面向视觉定位网络智能体的流水线感知端到端红队攻击框架。
提出 SPECGUARD，用 Lean 证书在编码 Agent 执行前证明任务冲突
Published Oct 7
Evaluated models GPT-5.6 Sol , Claude Opus 5 , Claude Fable 5 and others4 Abstract 提出预执行冲突检测与证明框架，在多个基准和真实仓库中成功证明任务与测试不可同时满足。
评测多智能体在开放式科研任务中找回预设子发现的能力
Published Oct 7
Evaluated models Gemini 3.1 Pro , GPT-5.5 , Claude Opus 4.8 and others7 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。