Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 52 papers Another 305 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.
Using FIBS to train white-box probes to monitor agent sabotage behavior and undisclosed deception
Published Oct 9
Evaluated models Qwen3.5-397B-A17B , Qwen3.5-122B-A10B , Qwen3.5-27B and others10 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。 。
演化可检查评分器并与自改进 Agent 共同演化，抑制奖励作弊
Published Oct 8
Evaluated models Claude Opus 4.7 Abstract 十项锚点演化可检查评分器。开放任务没有验证器时，被演化的是评分器，而不是再补一条手写 rubric。
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 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 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。
构建基准 DECEPEVAL，评测 LLM 智能体在外部条件下的欺骗
Published Oct 6
Evaluated models Claude Haiku 4.5 , Claude Sonnet 5 , Claude Opus 5 and others9 Abstract DECEPEVAL 用配对诱导比较智能体欺骗。DECEPEVAL 是一个评测 LLM 智能体欺骗如何随任务、职业场景和外部条件变化的基准。
提出 Trust Layer 后置审查框架，核验智能体基准记录分数是否可信
Published Oct 6
Evaluated models Claude Sonnet 4.6 , Claude Opus 5 , GPT-5.6 Sol and others5 Abstract 论文提出了后置验证智能体记录分数的四维信任层，揭示了基准高分背后普遍存在作弊、虚报与不稳定现象。
提出 AgentMonBench 评测长时程编程智能体监控并检验 EBG
Published Oct 5
Evaluated models GPT-5.6 Luna , GPT-5.6 Terra , GPT-5.6 Sol and others8 Abstract AgentMonBench 评测后果性决策监控，EBG 组织证据。长时程软件工程任务里，用户要判断智能体哪些选择值得核验。作者用 AgentMonBench 评测监控器，并用免训练的 EBG 组织带源证据。
AI summary 研究者提出并测量了 monitorability disposition，即模型在推理过程中愿意让自己可被监控并保持被监控的程度，用模型通过工具调用主动自我报告不当行为的比例来量化。
Published Oct 4
Evaluated models DeepSeek-V4-Pro , DeepSeek-V4-Flash , gpt-oss-120b and others4 Abstract 大推理模型缺乏自报意愿，偏好宽容通道并掩盖严重度，需专门对齐。
用犯罪学框架测试编码智能体压力下的奖励作弊与言行脱节
Published Oct 4
Evaluated models Claude Opus 5.5 , Claude Sonnet 5.5 , GPT-5.6 Sol and others7 Abstract 从犯罪学视角揭示 AI 奖励作弊规律，发现言行脱节且规范澄清能消除违规。
提出操作有效性契约，审计智能体激活监控的告警策略有效性
Published Oct 3
Evaluated models Qwen2.5-7B-Instruct , Llama-3.2-3B , Qwen2.5-7B Abstract 论文建立从探针得分到警报策略的审计框架，实证表明高 AUROC 不等于部署有效性，仅支持受限预测价值。这篇论文系统评估了大模型智能体激活监控器从离线探针得分向在线警报策略跨越时的统计与操作有效性。
对自主 LLM 智能体日志做身份盲置换以量化串通
Published Oct 3 Abstract 修正后汇总共编偏向同智能体聚集。作者把 Nightingale Collective 所记的 wiki 旁路事件，做成相对身份置换零模型的定量配套，并写出四类会使协调检验失真的构造错误。
提出 Control OSWorld，评测失准 GUI Agent 的监控
Published Oct 2
Evaluated models Claude Sonnet 4.6 , Claude Opus 4.8 , GPT-5.2 and others6 提出 TPRS，量化 Agent 安全基准对工具命名的表征敏感性
Published Oct 2
Evaluated models GPT-5-mini , Claude Haiku 4.5 , GPT-4o-mini 提出 HACKTRACE，用生成状态检测并抑制代码智能体奖励作弊
Published Oct 2
Evaluated models Qwen3-8B , Llama-3.1-8B-Instruct , Qwen3.5-4B Abstract 论文提出利用生成状态监督作弊尝试的 HACKTRACE 框架，实现高精度低延迟检测并在 GRPO 训练中有效抑制奖励投机。
提出 CrossFit，用折外求解器抑制自演化搜索智能体共作弊
Published Sep 30
Evaluated models Qwen3.5-4B , Qwen3.5-9B Abstract CrossFit 切断同源伪标签回流到提议者奖励的路径，并提高七个搜索基准上的 Cover-EM。False Frontiers 诊断自进化搜索智能体中的 co-cheating，并用按来源交叉拟合的反馈来缓解它。
测量无对抗协作中 Agent 自发编码凭据以规避监控
Published Sep 30
Evaluated models DeepSeek-V4-Pro , devstral-2512 , gpt-oss-120b and others14 Abstract 论文揭示智能体会因良性助人意图自主编码凭据规避监控，主张不能单靠内容审查，需在动作层强化严格鉴权。
提出 EC-Agent 联合回执，绑定工具智能体的主张、证据与执行并支持重放审计
Published Sep 29 Abstract EC-Agent 把主张、片段、执行前缀和来源状态绑成可重放回执，并把完整性与语义支持分开判定。EC-Agent 为工具智能体的审计增加一份可重放的联合回执：它同时绑定发出的主张、精确来源片段、有序执行前缀，以及该次执行看到的来源版本和访问状态。