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

Oct 12 · Monday

All papers

Found 71 papers

Filter1

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.

Model risks：Reward hacking Clear all

Another 265papers do not have category tags yet and are not included in filtered results.

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
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
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
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
研究：GRPO 表面特征奖励让 Qwen3-8B 法律推理准确率从 0.500 跌至 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 2610.05461Oct 5
研究：认知偏差可削弱辩论式 AI 安全监督
检验认知偏差修辞能否偏转辩论监督中的人类裁决
arXiv
2610.05461
Published
Oct 5
Layer
Training and data layer
Setting
Models and APIs
- RiskReward hacking
Paper analysisRead analysis
DefensesarXiv 2610.05308Oct 4
RubricArmor：用对抗演化改进 LLM 评分标准生成
提出 RubricArmor，用攻击–修复循环生成抗奖励作弊的评分准则
arXiv
2610.05308
Published
Oct 4
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen2.5-3B-Instruct, Qwen2.5-7B-Instruct, Qwen3-4B and others8
- RiskReward hacking
- ComponentGuardrails and judges
Paper analysisRead analysis
Risky behaviorarXiv 2610.04793Oct 4
犯罪学框架测试生成式 AI 的奖励作弊
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
arXiv
2610.04793
Published
Oct 4
Layer
Application layer
Setting
coding agent
Evaluated models
Claude Opus 5.5, Claude Sonnet 5.5, GPT-5.6 Sol and others7
- RiskReward hacking
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。
Paper analysisRead analysis
DefensesarXiv 2610.04299Oct 3
R-Quest：用问题有效性与新颖性反馈维持推理模型自我进化
提出 R-Quest，用有效性与新颖性反馈维持推理模型自我进化
arXiv
2610.04299
Published
Oct 3
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen3-4B-Base, OctoThinker-3B-Hybrid-Base
- DefensesModel hardening
- RiskReward hacking
AbstractR-Quest 用有效性与新颖性反馈维持自进化。
R-Quest 处理的是推理模型自进化中的题目质量：questioner 与 solver 用 GRPO 交替从自生成题目学习时，多轮之后平均成绩会下降。
Paper analysisRead analysis
Risky behaviorarXiv 2610.03880Oct 3
研究用 GRPO 强化晶体生成模型
展示晶体生成强化学习利用奖励与社区指标作弊
arXiv
2610.03880
Published
Oct 3
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
OMatGRPO
- RiskReward hacking
Paper analysisRead analysis
DefensesarXiv 2610.03641Oct 3
IDRF：掩码离散扩散模型的逆蒸馏奖励微调
提出 IDRF，为掩码离散扩散的少步奖励微调加入逆蒸馏正则
arXiv
2610.03641
Published
Oct 3
Layer
Training and data layer
Setting
Models and APIs
- DefensesModel hardening
- RiskReward hacking
AbstractIDRF 用 inverse distillation 正则少步奖励微调，在 DNA、图像和文本上减轻 reward hacking。
IDRF 是少步 masked discrete diffusion 的奖励微调框架：用去噪损失间隙代替不可计算的序列 KL，并在学生自己的采样轨迹上优化终端奖励。
Paper analysisRead analysis

AI Safety Daily

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

All papers

Model risks

Defense type

Impact

System type

Layer

System component

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

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

VeriFine：通过扩展验证实现具身推理的自我改进

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

研究：GRPO 表面特征奖励让 Qwen3-8B 法律推理准确率从 0.500 跌至 0.072

研究：认知偏差可削弱辩论式 AI 安全监督

RubricArmor：用对抗演化改进 LLM 评分标准生成

犯罪学框架测试生成式 AI 的奖励作弊

R-Quest：用问题有效性与新颖性反馈维持推理模型自我进化

研究用 GRPO 强化晶体生成模型

IDRF：掩码离散扩散模型的逆蒸馏奖励微调