作者位次 #2/4ACL 2026Poster· Natural Language Processing
P ro A ctor: Timing-Aware Reinforcement Learning for Proactive Task Scheduling Agents
Lei Ding · Bin He · Chenguang Wang · Yang Liu
摘要
Proactive task-oriented agents must autonomously anticipate user needs, identify actionable opportunities, and trigger software actions at appropriate moments—fundamentally shifting from reactive systems that await explicit instructions. However, existing approaches lack generalizable end-to-end...