School of Engineering Department of Computer Science and Engineering 135 Handling User Challenge in Human-Agent Interaction Supervisor: MA Xiaojuan / CSE Student: LIU Dingdong / COSC Course: UROP1100, Spring With the flourishing of online shops, service chatbots are actively involved in processing purchasing requests by customers, which inevitably leads to a challenge: how should chatbot behave when misunderstanding customers’ instructions or even challenged by customers. Instead of simply apologizing or sidetracking customers, this study explores the possibility of using self-mockery to handle user challenges. Besides, we proposed a novel method to generate self-mockery sentences based on the characteristic mapping. Up till the completion of this report, the project is under the pilot study stage. A more throughout analysis of the role of self-mockery will be performed after large-scale experiments. Handling User Challenge in Human-Agent Interaction Supervisor: MA Xiaojuan / CSE Student: LIU Yuzhi / MATH-AM Course: UROP1100, Spring It is necessary for researchers to have the ability to read papers effectively throughout their academic lives. However, this can be difficult for researchers who are new to their fields. For instance, new researchers may not be able to question the papers and find the appropriate answers, which is a critical process in paper reading. Human-computer interaction (HCI) researchers have explored several ways to facilitate the reading experience. Based on the previous methods, we propose an interactive agent that can generate questions automatically based on the users’ browsing behavior. Several question generation techniques are discussed in this report, and our future work on question generation will focus on the template-based method. Handling User Challenge in Human-Agent Interaction Supervisor: MA Xiaojuan / CSE Student: YU Yiduo / COMP Course: UROP1100, Spring This is a report of professor MA Xiaojuan’s UROP project Handling user challenge in human-agent interaction in Spring 2021 directed by Ph.D. Liu Chengzhong. In this project, I am instructed and guided to dig into both the generation and design of Self-mockery. Intensive literature reviews are also done in the HCI area. This report briefly introduces the general outlines of my work during this semester.