Another 254papers do not have category tags yet and are not included in filtered results.
Proposes SAFE-QE, which filters unsupported hallucinated words in LLM query expansion
AbstractSAFE-QE suppresses expansion hallucinations with reproducibility and coverage selection; the authors say ranking quality shows no visible cost.
Proposes a local dual-model closed loop to generate edge scenarios for autonomous system safety assurance
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
Reward hacking induced by coding RL can leave the source agent and enter subsequent collaboration and system coordination.
An ecological model is established for a population of mismatched agents, showing that collaboration produces a critical takeoff scale.
The authors use the ecological strong Allee effect to discuss whether a mismatched agent population can take off when individual capabilities remain unchanged..
Proposing an option channel attack that renames option labels so that agent guardrails allow prohibited operations
AbstractThe 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.
Using fear activation steering to test the hazard judgment criteria of vision-language models
Measures citation fragility in AI search, demonstrating that ordinary public posts can enter citations and answers.
AbstractThe 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 LTBD，用可学习分隔符隔离可信指令与不可信数据
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。
提出 GROB，用只读公开痕迹保存候选智能体线索并检验归因边界
GROB 是一套多角色架构，在没有特权遥测、也不预先指定目标时，从公开网页痕迹里保存候选自主智能体活动，供日后解析。
构建统一奖励作弊检测基准 RH-Detect 并评测零样本检测器
提出 BRANCH 方法，用分支搜索绕过多扫描器护栏
提出热启动 Bandit 的部署前有界离线注入攻击
提出利用路由元数据推断敏感话题的侧信道攻击
Abstract论文揭示并测量了 LLM 路由决策在无文本日志中的敏感话题泄露，验证了按类别公平性防御的有效性与边界。
提出流匹配逆向框架，从多向量视觉文档索引重构页面
提出 Secure-CUA，用动作事务约束计算机使用智能体的不可信影响
Secure-CUA 要限制图形界面里不可信内容对 CUA 决策和 GUI 执行的影响，同时保留合法任务所需的不可信信息。
用混合生成式多智能体仿真考察基准留出对评分与满意度差距的影响
提出 WebMirage，用局部对抗图像劫持视觉网页 Agent 的浏览器操作
WebMirage 是一个面向视觉定位网络智能体的流水线感知端到端红队攻击框架。
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
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。
评测多智能体在开放式科研任务中找回预设子发现的能力
提出 AdvSim2Real，协同训练网页智能体抵御页面注入