Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 239 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.
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.
Proposes a local dual-model closed loop to generate edge scenarios for autonomous system safety assurance
Published Oct 9
Evaluated models PPO Abstract Local closed-loop generation of JSON edge cases.The authors built a local agentic loop that runs on a laptop to generate edge cases for safety arguments of autonomous systems, rather than releasing a new public test set.
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.
Proposing an option channel attack that renames option labels so that agent guardrails allow prohibited operations
Published Oct 9
Evaluated models LAYA-TD , LAYA-EN , LAYA-ML and others5 Abstract The authors' evaluation indicates that typed models should not serve as final safety arbiters; they are susceptible to off-policy text and option name manipulation, and confidence filtering cannot resist attacks.
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 LTBD，用可学习分隔符隔离可信指令与不可信数据
Published Oct 8
Evaluated models Llama3-8B-Instruct , Llama3.1-8B-Instruct , Falcon3-7B-Instruct and others4 Abstract LTBD 只训练四个分隔符嵌入。LTBD 是一种不改基座权重的提示注入防御：只学习用来标出可信指令与不可信数据边界的四个 token 嵌入。
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。
构建统一奖励作弊检测基准 RH-Detect 并评测零样本检测器
Published Oct 8
Evaluated models Qwen 3.5 Flash , Gemini 3.1 Flash Lite , Grok 4.1 Fast and others7 提出 BRANCH 方法，用分支搜索绕过多扫描器护栏
Published Oct 8
Evaluated models Meta Llama Guard 3 8B , Meta Llama Guard 7B , Meta Llama Guard 3 1B and others18 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 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 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 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 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。
提出 CARE 框架，在误分类风险约束下减少人机协作的人工查询
Published Oct 7
Evaluated models Qwen3-VL-2B-Instruct , Perspective , Moderation and others9 Abstract CARE 以残差校正加逐步校准做人机决策，四个任务上少查询并控制集成风险。CARE 是面向人机协同二分类的端到端流水线，要在误分类风险不超过用户容忍的前提下减少人类查询。设定是 i.i.d.数据流、人类 oracle 标签正确、AI 为任意黑盒概率分类器。
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。