作者位次 #5/8ICLR 2026Oral
RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
Zeyi Liao · Jaylen Jones · Linxi Jiang · Yuting Ning · Eric Fosler-Lussier · Yu Su · Zhiqiang Lin · Huan Sun
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Zeyi Liao · Jaylen Jones · Linxi Jiang · Yuting Ning · Eric Fosler-Lussier · Yu Su · Zhiqiang Lin · Huan Sun
Ashley Lewis · Andrew Perrault · Eric Fosler-Lussier · Michael White
Hallucination—defined here as generated statements unsupported or contradicted by available evidence or conversational context—remains a major obstacle to using conversational AI systems in settings that demand factual reliability. Existing metrics evaluate isolated responses or treat unverifiabl...