Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulation
Tong Zhang, Chen Huang, Yang Deng, Hongru Liang, Jia Liu, Zujie Wen, Wenqiang Lei, Tat-Seng Chua
摘要
We investigate non-collaborative dialogue agents, which are expected to engage in strategic conversations with diverse users, for securing a mutual agreement that leans favorably towards the system's objectives. This poses two main challenges for existing dialogue agents: 1) The inability to integrate user-specific characteristics into the strategic planning, and 2) The difficulty of training strategic planners that can be generalized to diverse users. To address these challenges, we propose TRIP to enhance the capability in tailored strategic planning, incorporating a user-aware strategic planning module and a population-based training paradigm. Through experiments on benchmark non-collaborative dialogue tasks, we demonstrate the effectiveness of TRIP in catering to diverse users.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper9
- A Dual-Mind Framework for Strategic and Expressive Negotiation AgentYutong Liu, Lida Shi, Rui Song, Hao XuACL 2025 · 被引用 4 次
- DialogXpert: Driving Intelligent and Emotion-Aware Conversations Through Online Value-Based Reinforcement Learning with LLM PriorsTazeek Bin Abdur Rakib, Ambuj Mehrish, Lay-Ki Soon, Wern Han Lim 等AAAI 2026 · 被引用 3 次
- Simulating Before Planning: Constructing Intrinsic User World Model for User-Tailored Dialogue Policy PlanningTao He, Lizi Liao, Ming Liu, Bing QinSIGIR 2025 · 被引用 2 次
- Thinking Alignment of Scenario-Oriented User SimulationXiaoting Wu, Yi Huang, Chunyang Gao, Mengfei Guo 等ACL 2026
- How to Enable Effective Cooperation Between Humans and NLP Models: A Survey of Principles, Formalizations, and BeyondChen Huang, Yang Deng, Wenqiang Lei, Jiancheng Lv 等ACL 2025
它引用的顶会 Paper13
- Self-Consistency Improves Chain of Thought Reasoning in Language ModelsXuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le 等ICLR 2023 · 被引用 681 次
- Evaluating and Inducing Personality in Pre-trained Language ModelsGuangyuan Jiang, Manjie Xu, Song-Chun Zhu, Wenjuan Han 等NeurIPS 2023 · 被引用 192 次
- Language Agents with Reinforcement Learning for Strategic Play in the Werewolf GameZelai Xu, Chao Yu, Fei Fang, Yu Wang 等ICML 2024 · 被引用 145 次
- MIC: Mining Interclass Characteristics for Improved Metric LearningBiagio Brattoli, Karsten Roth, Björn OmmerICCV 2019 · 被引用 100 次
- Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMsMaarten Sap, Ronan Le Bras, Daniel Fried, Yejin ChoiEMNLP 2022 · 被引用 92 次
相关 Paper
- Battling against Tough Resister: Strategy Planning with Adversarial Game for Non-collaborative DialoguesHaiyang Wang, Zhiliang Tian, Yuchen Pan, Xin Song 等ACL 2025 · 被引用 3 次
- Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue PolicyWenqiang Lei, Yao Zhang, Feifan Song, Hongru Liang 等SIGIR 2022 · 被引用 7 次
- One Cannot Stand for Everyone! Leveraging Multiple User Simulators to train Task-oriented Dialogue SystemsYajiao Liu, Xin Jiang, Yichun Yin, Yasheng Wang 等ACL 2023 · 被引用 5 次
- A Mixture-of-Expert Approach to RL-based Dialogue ManagementYinlam Chow, Aza Tulepbergenov, Ofir Nachum, Dhawal Gupta 等ICLR 2023 · 被引用 2 次
- Cooper: Coordinating Specialized Agents towards a Complex Dialogue GoalYi Cheng, Wenge Liu, Jian Wang, Chak Tou Leong 等AAAI 2024 · 被引用 34 次
