{"ID":2866316,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.19695","arxiv_id":"2509.19695","title":"DyBBT: Dynamic Balance via Bandit-inspired Targeting for Dialog Policy with Cognitive Dual-Systems","abstract":"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 structured cognitive state space capturing dialog progression, user uncertainty, and slot dependency. DyBBT proposes a bandit inspired meta-controller that dynamically switches between a fast intuitive inference (System 1) and a slow deliberative reasoner (System 2) based on real-time cognitive states and visitation counts. Extensive experiments on single- and multi-domain benchmarks show that DyBBT achieves state-of-the-art performance in success rate, efficiency, and generalization, with human evaluations confirming its decisions are well aligned with expert judgment.","short_abstract":"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 structured cognitive state...","url_abs":"https://arxiv.org/abs/2509.19695","url_pdf":"https://arxiv.org/pdf/2509.19695v3","authors":"[\"Shuyu Zhang\",\"Yifan Wei\",\"Jialuo Yuan\",\"Xinru Wang\",\"Yanmin Zhu\",\"Bin Li\",\"Yujie Liu\"]","published":"2025-09-24T02:06:26Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.IR\"]","methods":"[\"LoRA\"]","has_code":false}