作者位次 #3/7ACL 2026Poster· Natural Language Processing
D y BBT : Dynamic Balance via Bandit-inspired Targeting for Dialog Policy with Cognitive Dual Systems
Shuyu Zhang · Yifan Wei · Jialuo Yuan · Xinru Wang · Yanmin Zhu · Yujie Liu · Bin Li
摘要
Task oriented dialog systems often rely on static exploration strategies that do not adapt to dynamic dialog contexts, leading to inefficient exploration and suboptimal performance. We propose DyBBT, a novel dialog policy learning framework that formalizes the exploration challenge through a stru...