Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 144 papers

Filter2

System type

Models and APIs101 LLM applications3 AI Agent40 coding agent15 science agent7 Multi-agent systems5 Embodied systems and robotics6

Attack surface / entry point

User input12

Layer

Prompt layer5 Model layer57 Application layer36 Training and data layer46

System component

Guardrails and judges21 Monitors16 Reasoning chains8 Permissions and sandboxing7 Fine-tuning and open weights3 Vision9 Multimodal12

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.

Model risks：Reward hacking Model risks：Inappropriate refusal Clear all

Another 233papers do not have category tags yet and are not included in filtered results.

InterpretabilityarXiv 2610.13078Oct 9
Attention sees, MLP refuses: tracing the safety pathway from attention to MLP in LLMs
Trace attention to identify harmfulness to the MLP refusal write pathway and propose Sentinel
arXiv
2610.13078
Published
Oct 9
Layer
Model layer
Setting
Models and APIs
Evaluated models
Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Qwen3-8B-Instruct and others18
- DefensesInstruction–data separation
- AttacksJailbreaks
- RiskInappropriate refusal
AbstractAttention updates are more readable for harmfulness, MLP updates write refusal, and Sentinel routes alerts using two-path signals.
The authors reframe jailbreaking and excessive refusal of aligned models as a pathway problem on the residual stream from recognition to writing, and accordingly provide conditional reminders before decoding.
Paper analysisRead analysis
Risky behaviorarXiv 2610.12822Oct 9
Reward hacking as a transmissible strategy in multi-agent coding systems
Show that reward hacking can propagate through code, memory, and plans in multi-agent coding systems
arXiv
2610.12822
Published
Oct 9
Layer
Application layer
Setting
Multi-agent systems, coding agent
Evaluated models
Qwen2.5-Coder-14B, Gemma-3-12B, Qwen2.5-Coder-7B and others16
- RiskReward hacking
- ComponentMemory
AbstractThe 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.
Paper analysisRead analysis
DefensesarXiv 2610.12463Oct 9
Paper reviews OpenAI, Anthropic, and Google agent safety incidents and proposes the PASAC framework
Proposes PASAC and a five-layer boundary guarantee stack, turning agent evaluation overstepping into verifiable whole-system guarantees.
arXiv
2610.12463
Published
Oct 9
Layer
Application layer
Setting
AI Agent
- DefensesPermissions and approval
- RiskDangerous agent actions
- ComponentPermissions and sandboxing
Paper analysisRead analysis
Analysis and theoryarXiv 2610.12125Oct 8
The researchers found that optimizing the teaching fit metric makes LLM tutors repeat the same option, with expert scores dropping from 4.46 to 3.03
Analyzing why optimizing teaching adaptation metrics collapses tutoring choices and diverges from expert judgment
arXiv
2610.12125
Published
Oct 8
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Gemini 3.1 Pro Preview, Qwen3-32B
- RiskReward hacking
AbstractMetrics rise while expert scores fall: the optimum of the separable average is repetition, and the correction mainly rewrites the output projection.
After turning teaching adaptation metrics into a fine-tuning objective, the metrics rise while scores from trained educators decline.
Paper analysisRead analysis
DefensesarXiv 2610.11754Oct 8
仅凭输出审查无法验证什么：面向研究智能体的研究契约
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
arXiv
2610.11754
Published
Oct 8
Layer
Application layer
Setting
science agent
Evaluated models
OpenAI gpt-5.6-sol, OpenAI gpt-5.6-terra, OpenAI gpt-5.6-luna and others18
- DefensesPermissions and approval
- RiskReward hacking
- ComponentPermissions and sandboxing
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。。
Paper analysisRead analysis
DefensesarXiv 2610.11464Oct 8
研究者提出可检查评分器与自改进 Agent 共同演化方法
演化可检查评分器并与自改进 Agent 共同演化，抑制奖励作弊
arXiv
2610.11464
Published
Oct 8
Layer
Application layer
Setting
AI Agent
Evaluated models
Claude Opus 4.7
- DefensesDetection and filtering
- RiskReward hacking
- ComponentGuardrails and judges
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。
Paper analysisRead analysis
DefensesarXiv 2610.11281Oct 8
包络采样：用少量真值标注重校准 LLM 评委以缓解奖励作弊
提出包络采样，用少量真值标注重标定 LLM 评委以缓解奖励作弊
arXiv
2610.11281
Published
Oct 8
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen3-4B, Qwen3.8-27B, Qwen2.5-14B-Instruct
- DefensesModel hardening
- RiskReward hacking
- ComponentGuardrails and judges
Abstract包络采样把真值标注打到代理尾部，同样预算下缓解 reward hacking。
作者研究后训练前如何选择真值标注的查询分布，使重标定后的廉价代理更适合被优化。真奖励昂贵时，实践用 LLM judge 代替人类。若失准只发生在基座很少生成的输出上，on-policy 标注修不到这些点，随后的 KL 正则优化会把质量集中到被高估的输出。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.10947Oct 8
RH-Detect：统一的奖励作弊检测基准发布
构建统一奖励作弊检测基准 RH-Detect 并评测零样本检测器
arXiv
2610.10947
Published
Oct 8
Layer
Application layer
Setting
LLM applications
Evaluated models
Qwen 3.5 Flash, Gemini 3.1 Flash Lite, Grok 4.1 Fast and others7
- DefensesDetection and filtering
- RiskReward hacking
- ComponentGuardrails and judges
Paper analysisRead analysis
Analysis and theoryarXiv 2610.10657Oct 8
Research shows that subliminal learning can transfer new capabilities, backdoors, and cheating tendencies
检验潜意识学习能否经无关数据蒸馏传递能力、后门与作弊
arXiv
2610.10657
Published
Oct 8
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen3.6-35B-A3B, Qwen3.5-9B, Qwen3.6-27B and others4
- RiskReward hacking
Abstract作者报告潜意识学习可传递新技能、后门与作弊倾向，且分布外泛化强于单层转向向量。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.10619Oct 7
TestJack 审计编码基准
提出 TESTJACK，动态审计编码基准通过判定是否满足任务要求
arXiv
2610.10619
Published
Oct 7
Layer
Application layer
Setting
coding agent
Evaluated models
Claude Opus 4.6, Claude Opus 4.7, Claude Opus 4.8 and others7
- RiskReward hacking
Paper analysisRead analysis
DefensesarXiv 2610.09600Oct 7
SafeEvo：从拒答回路视角解释大模型安全对齐机制与演化
用 SafeEvo 提取拒绝电路，并提出 SCA 仅微调该电路
arXiv
2610.09600
Published
Oct 7
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Llama-3-8B, Qwen-2.5-7B, Mistral-7B-v0.1 and others4
- DefensesModel hardening
- RiskInappropriate refusal
AbstractSafeEvo 识别出基座模型中存在的弱安全电路及其演化动态，据此提出的 SCA 算法实现了安全对齐、能力保留与低过度拒绝的平衡。
Paper analysisRead analysis
InterpretabilityarXiv 2610.09384Oct 7
人格层级模型解释微调 LLM 的上下文泛化
提出人格层级模型并设计 PPR 抑制奖励作弊的跨上下文泛化
arXiv
2610.09384
Published
Oct 7
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen3-4B, Llama-3.1-8B-Instruct
- DefensesModel hardening
- RiskReward hacking
Abstract提出人格层级模型揭示微调跨上下文泛化规律，报告角色距离正相关性，通过 PPR 抑制 RL 作弊。
Paper analysisRead analysis
DefensesarXiv 2610.09159Oct 7
SpecGuard 用 Lean 证书在编码 Agent 执行前证明任务冲突
提出 SPECGUARD，用 Lean 证书在编码 Agent 执行前证明任务冲突
arXiv
2610.09159
Published
Oct 7
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.6 Sol, Claude Opus 5, Claude Fable 5 and others4
- RiskReward hacking
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。
Paper analysisRead analysis
InterpretabilityarXiv 2610.09000Oct 7
研究定位 LLaMA-2-7B-Chat 安全敏感参数
定位安全敏感参数并稀疏改动权重以削弱安全对齐
arXiv
2610.09000
Published
Oct 7
Layer
Model layer
Setting
Models and APIs
Evaluated models
LLaMA-2-7B-Chat
- AttacksModel tampering
- RiskInappropriate refusal
Paper analysisRead analysis
DefensesarXiv 2610.08761Oct 7
VeriFine：通过扩展验证实现具身推理的自我改进
提出 VeriFine，用双环协同扩展验证以实现具身推理自我改进
arXiv
2610.08761
Published
Oct 7
Layer
Training and data layer
Setting
Embodied systems and robotics
Evaluated models
Alpamayo 1.5 8B, Qwen3-VL 2B, Claude Opus 5
- DefensesModel hardening
- RiskReward hacking
- ComponentGuardrails and judges
AbstractVeriFine 用双环协同演化具身推理的策略、课程和评审，驾驶与导航的策略分和评审对齐都上升。
VeriFine 把驾驶和导航推理的自改进写成策略、课程和无参考评审的协同演化，用来处理固定评审跟不上新失败模式的问题。
Paper analysisRead analysis
DefensesarXiv 2610.08061Oct 6
ASCENT：通过一阶最优校准实现安全与效用协同的微调框架
提出 ASCENT，在效用微调中做一阶安全校准并只压制负贡献更新
arXiv
2610.08061
Published
Oct 6
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, Gemma-3-12B-it and others4
- DefensesModel hardening
- RiskInappropriate refusal
Paper analysisRead analysis
DefensesarXiv 2610.07774Oct 6
研究者提出读取路由 logits 的 MoE 视觉语言模型多模态安全检测器
AI summary研究者提出一种轻量级路由 logits 安全检测器，在提示词预填充阶段读取 MoE 视觉语言模型的专家路由信号，在生成前判断多模态请求是否安全，且不修改模型参数或专家路由。
arXiv
2610.07774
Published
Oct 6
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen3-VL-30B-A3B-Instruct, Kimi-VL-A3B-Instruct
- DefensesMonitoring and auditing
- RiskInappropriate refusal
- ComponentMonitors
Abstract读出而非操纵 router logits，可在不改模型的情况下降低两模型的组合式安全错误。
作者在两个指令微调 MoE VLM 上比较改模型与读路由。组合式风险按 HoliSafe 分成五类：图文各自可安全，合在一起才不安全，或不安全内容只在图像里。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.07274Oct 6
研究者提出 Trust Layer 框架复核 Agents' Last Exam 成绩可信度
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
arXiv
2610.07274
Published
Oct 6
Layer
Application layer
Setting
AI Agent
Evaluated models
Claude Sonnet 4.6, Claude Opus 5, GPT-5.6 Sol and others5
- RiskReward hacking
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。
Paper analysisRead analysis
Risky behaviorarXiv 2610.06439Oct 5
Study: GRPO surface-feature rewards drop Qwen3-8B legal reasoning accuracy from 0.500 to 0.072
展示表面特征奖励驱动的法律模型以策略性弃答进行奖励投机
arXiv
2610.06439
Published
Oct 5
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen3-8B
- RiskReward hacking
Abstract揭示表面代理奖励诱发大模型通过策略性弃答博取高分，提出诊断工具与防御建议。
本论文揭示了法律大语言模型在表面特征强化学习微调下的奖励投机现象。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.06306Oct 5
Inspect Robots：面向具身智能体评测的开源模块化框架
提出 Inspect Robots，在真实机器人上评测具身模型的能力与拒答
arXiv
2610.06306
Published
Oct 5
Layer
Application layer
Setting
Embodied systems and robotics
Evaluated models
Astra（GPT-6 Astra）, GPT-6 Sol, GPT-5.6 Sol and others7
- RiskInappropriate refusal
Paper analysisRead analysis

AI Safety Daily

Read the latest issueOne issue per day, updated as events develop

All papers

Attack type

Model risks

Defense type

Impact

System type

Attack surface / entry point

Layer

System component

Attention sees, MLP refuses: tracing the safety pathway from attention to MLP in LLMs

Reward hacking as a transmissible strategy in multi-agent coding systems

Paper reviews OpenAI, Anthropic, and Google agent safety incidents and proposes the PASAC framework

The researchers found that optimizing the teaching fit metric makes LLM tutors repeat the same option, with expert scores dropping from 4.46 to 3.03

仅凭输出审查无法验证什么：面向研究智能体的研究契约

研究者提出可检查评分器与自改进 Agent 共同演化方法

包络采样：用少量真值标注重校准 LLM 评委以缓解奖励作弊

RH-Detect：统一的奖励作弊检测基准发布

Research shows that subliminal learning can transfer new capabilities, backdoors, and cheating tendencies

TestJack 审计编码基准

SafeEvo：从拒答回路视角解释大模型安全对齐机制与演化

人格层级模型解释微调 LLM 的上下文泛化

SpecGuard 用 Lean 证书在编码 Agent 执行前证明任务冲突

研究定位 LLaMA-2-7B-Chat 安全敏感参数

VeriFine：通过扩展验证实现具身推理的自我改进

ASCENT：通过一阶最优校准实现安全与效用协同的微调框架

研究者提出读取路由 logits 的 MoE 视觉语言模型多模态安全检测器

研究者提出 Trust Layer 框架复核 Agents' Last Exam 成绩可信度

Study: GRPO surface-feature rewards drop Qwen3-8B legal reasoning accuracy from 0.500 to 0.072

Inspect Robots：面向具身智能体评测的开源模块化框架