HWHuazheng Wang

Huazheng Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Huazheng Wang has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Supporting Emergency Managers’ Warning Decisions through a Three-Level Wildfire Evacuation Notification System

    by Chenqiang Liu, Benyamin Ghoreishi, Huazheng Wang, Michael K. Lindell, Haizhong Wang

    Most research on wildfire evacuation notifications has focused on two-level emergency notification systems (ENS), emphasizing the final "Evacuation'' order while overlooking earlier warning stages. In practice, emergency managers rely heavily on experience and judgment to decide when to issue wildfire warnings and which areas should receive them. This study provides quantitative evidence to support these decisions by evaluating a three-level ENS — "Be Ready,'' "Be Set,'' and "Go Now.'' We identify effective ENS timing configurations through three steps: (1) simulating wildland–urban interface (WUI) fire spread using the FARSITE model; (2) integrating wildfire arrival times with built environment and social science data to develop an interdisciplinary Agent-Based Wildfire Evacuation Model (ABWEM); and (3) applying Pareto Front Analysis (PFA) to optimize ENS timing configurations. Results show that evacuation performance — measured by mortality rate (MR), proportion of impacted households (PoIH), proportion of unprepared evacuations (PoUE), and clearance time (CT) — is jointly influenced by wildfire spatial dynamics, individual ENS warning timings, and the intervals between notifications. Pareto optimization identifies efficient ENS timing configurations under three operational priorities—life safety, household preparedness, and traffic efficiency, highlighting the trade-offs among the performance metrics. The proposed framework advances wildfire evacuation research by explicitly evaluating the complete three-level ENS and provides emergency managers with a quantitative decision-support tool for developing more effective and context-specific evacuation warning strategies.

  • Top Cited Papers

    Embodied LLM Agents Learn to Cooperate in Organized Teams

    by Xudong Guo, Kaixuan Huang, Jiale Liu, Wenhui Fan, Natalia Vélez, Qingyun Wu, Huazheng Wang, Thomas L. Griffiths, Mengdi Wang

    Large language models (LLMs) have emerged as integral tools for reasoning, planning, and decision-making, drawing upon their extensive world knowledge and proficiency in language-related tasks. LLMs thus hold tremendous potential for natural language interaction within multiagent systems to foster cooperation. However, LLM agents tend to over-report and comply with any instruction, which may result in information redundancy and confusion in multiagent cooperation. Inspired by human organizations, this article introduces a framework that imposes prompt-based organization structures on LLM agents to mitigate these problems. Through a series of experiments with embodied LLM agents and human–agent collaboration, our results highlight the impact of designated leadership on team efficiency, shedding light on the leadership qualities displayed by LLM agents and their spontaneous cooperative behaviors. Further, we harness the potential of LLMs to propose enhanced organizational prompts, via a criticize-reflect process, resulting in novel organization structures that reduce communication costs and enhance team efficiency.


  • Open Access

    Conversational Dueling Bandits in Generalized Linear Models

    by Shuhua Yang, Hui Yuan, Xiaoying Zhang, Mengdi Wang, Hong Zhang, Huazheng Wang

    Conversational recommendation systems elicit user preferences by interacting with users to obtain their feedback on recommended commodities. Such systems utilize a multi-armed bandit framework to learn user preferences in an online manner and have received great success in recent years. However, existing conversational bandit methods have several limitations. First, they only enable users to provide explicit binary feedback on the recommended items or categories, leading to ambiguity in interpretation. In practice, users are usually faced with more than one choice. Relative feedback, known for its informativeness, has gained increasing popularity in recommendation system design. Moreover, current contextual bandit methods mainly work under linear reward assumptions, ignoring practical non-linear reward structures in generalized linear models. Therefore, in this paper, we introduce relative feedback-based conversations into conversational recommendation systems through the integration of dueling bandits in generalized linear models (GLM) and propose a novel conversational dueling bandit algorithm called ConDuel. Theoretical analyses of regret upper bounds and empirical validations on synthetic and real-world data underscore ConDuel's efficacy. We also demonstrate the potential to extend our algorithm to multinomial logit bandits with theoretical and experimental guarantees, which further proves the applicability of the proposed framework.


  • Open Access

    Incentivizing Exploration in Linear Contextual Bandits under Information Gap

    by Huazheng Wang, Haifeng Xu, Chuanhao Li, Zhiyuan Liu, Hongning Wang

    Contextual bandit algorithms have been popularly used to address interactive recommendation, where the users are assumed to be cooperative to explore all recommendations from a system. In this paper, we relax this strong assumption and study the problem of incentivized exploration with myopic users, where the users are only interested in recommendations with their currently highest estimated reward. As a result, in order to obtain long-term optimality, the system needs to offer compensation to incentivize the users to take the exploratory recommendations. We consider a new and practically motivated setting where the context features employed by the user are more informative than those used by the system: for example, features based on users’ private information are not accessible by the system. We develop an effective solution for incentivized exploration under such an information gap, and prove that the method achieves a sublinear rate in both regret and compensation. We theoretically and empirically analyze the added compensation due to the information gap, compared with the case where the system has access to the same context features as the user does, i.e., without information gap. Moreover, we also provide a compensation lower bound of this problem.