rohanpaul_ai· @rohanpaul_ai · X·· 5 小时前AI 评分
AgentHorizon评测长程计算机使用智能体
– arxiv.org/abs/2610.11050 Title: "AgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks"
– arxiv.org/abs/2610.11050
Title: "AgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks"
来源:rohanpaul_ai · x.com