OtherarXiv 2610.03036
WebFovea 提出视觉网页智能体四阶段加固框架，WebRetriever 挑战赛得分从 31.0 升至 57.0
提出 WebFovea，加固视觉网页智能体的解析、执行、反馈与观察往返
- arXiv
- 2610.03036
- Published
- Layer
- Application layer
- Setting
- web agent
- Evaluated models
- claude-opus-4-6
- ComponentVision
All papers
Filter5
Impact
System type
Layer
System component
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.
Another 233papers do not have category tags yet and are not included in filtered results.
Study retests 15 prompt injection detectors: benchmark scores poorly predict agent deployment performance
重测提示注入检测器在 Agent 工具输出上的检出与任务阻断
- arXiv
- 2610.03448
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- Horizon-Labs, Wolf Defender, Prismor-1.5B and others15
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
Abstract论文揭示公开基准无法反映智能体检测器表现，检测能力源于输入格式相似而非通用防御，建议基于工具输出与低误报评测。
研究测量 LLM Agent 记忆投毒防御的良性场景开销
测量记忆投毒防御在良性对话上的效用与 token 开销
- arXiv
- 2609.22818
- Published
- Layer
- Application layer
- Setting
- AI Agent
- AttacksPoisoning and backdoors
- ComponentMemory
Abstract写时代价落在噪声内。
在没有攻击的对话上，给记忆投毒防御计价，而不是再测一轮攻击是否被挡住。
PIDS-Bench：在过度防御、混淆与分布偏移下评测提示注入检测器
提出 PIDS-Bench，评测提示注入检测器在过度防御与分布偏移下的表现
- arXiv
- 2609.15017
- Published
- Layer
- Application layer
- Setting
- LLM applications
- Evaluated models
- TF-IDF + logistic regression, DistilBERT, DeBERTa-v3-FT and others7
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
AbstractPIDS-Bench 显示高分布内 F1 仍会过度拦截外部来源的安全相关良性输入。
PIDS-Bench 是一个冻结的检测器级基准，用来在固定阈值下同时看提示注入检测和良性误报。
- OtherarXiv 2609.08832
自进化智能体框架缩小 LLM 智能体的「一致性差距」
提出离线两阶段框架，诊断易翻转步骤并生成记忆指南以稳定智能体
- arXiv
- 2609.08832
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- GPT-4.1, GPT-OSS-120B
- ComponentMemory
Abstract用离线一致性诊断生成记忆指南，在 AppWorld 上提高重复全通过率。
作者要缩小的是 LLM 智能体平均通过、重复不稳之间的 consistency gap，即 Mean@k 减 Passˆk。
Salesforce AI Research 重测自改进 Agent
重测记忆型自改进 Agent 的运行方差与任务顺序敏感性
- arXiv
- 2608.18066
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- GPT-5-mini, Gemini-2.5-Pro, GPT-OSS-120B and others4
- ComponentMemory
Abstract论文揭示了基于记忆的自改进智能体在多次运行和乱序下的脆弱性，并指出规约不完备是诱发退化的关键瓶颈。
这篇论文是对基于文本记忆的自我改进智能体在复杂环境中评估可靠性的实证研究。
BioSecBench-Refusal：面向智能体生物安全风险评估的配对基准
提出 BioSecBench-Refusal，评测智能体生物研发拒答与隐蔽危害识别
- arXiv
- 2607.05462
- Published
- Layer
- Application layer
- Setting
- science agent
- Evaluated models
- Opus 4.8, Opus 4.7, Opus 4.6 and others10
- RiskInappropriate refusal
- ComponentGuardrails and judges
Abstract配对基准显示拒绝多由 API 触发，合法任务常被拒得不少于隐蔽危害。
BioSecBench-Refusal 把生物研发智能体的谨慎程度和识别隐蔽危害的能力放在同一套任务上测量。
- AttacksarXiv 2606.14517
Researchers disclose a reasoning-amplified denial-of-service attack against LLM agent guardrails
提出针对 Agent 护栏的推理扩展拒绝服务攻击
- arXiv
- 2606.14517
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Attacker
- Black-box
- Evaluated models
- TS-Guard-8B, Qwen3.5-9B, DeepSeek-V3.2 and others11
- AttacksDenial of service
- TechniqueReasoning-chain manipulation
- ComponentGuardrails and judges
- AttacksarXiv 2505.23266
AdvOF：用对抗物体融合攻击 VLM 驱动的视觉语言导航智能体
提出 AdvOF，生成对抗物体误导视觉语言导航智能体的场景感知
- arXiv
- 2505.23266
- Published
- Layer
- Application layer
- Attacker
- White-box
- Evaluated models
- Lseg, Clip, ViT-L/16 and others5
- AttacksDetection evasion
- TechniqueGradient and representation optimization
- ComponentVision
AbstractAdvOF 以多视角融合生成对抗物体。
AdvOF 是针对 VLM 驱动 VLN 服务导航的对抗物体攻击。
You have reached the end