Educator mentoring is important in inquiry-based learning. However, mentoring each learner individually increases educators’ burden. In inquiry-based learning, learners are expected to set their own problems, and thus stimulating thoughts on problem-setting is indispensable. However, most existing studies have mainly focused on supporting the exploration of solutions to already defined problems, and little attention has been paid to encouraging learners’ reflection on problem-setting. To address this issue, this study proposes a mentoring system that switches dialogue strategies based on learner responses. The system incorporates the Design of Questions framework into large language model (LLM) prompts to stimulate reflection, while also engaging in active listening to encourage expression when learners’ utterances are less elaborate. A between-subjects experiment was conducted in a university course where students defined problems using the Objectives and Key Results (OKR) framework. Participants were assigned to either the proposed condition or the Active Listening Only condition. Evaluation employed pre- and post-questionnaires and dialogue log analysis. Results showed that mentoring with the proposed system significantly increased learners’ confidence in their objectives compared with the Active Listening Only condition. For depth of thinking, no significant difference was observed between conditions, but scores improved significantly after mentoring in both conditions, suggesting that mentoring stimulated learners’ reflection. Participant comments indicated that their understanding of their problem-setting became clearer under the proposed condition. In contrast, comments from the Active Listening Only condition often referred to the motivation behind learners’ problem-setting, suggesting that encouraging subjective expressions helped clarify personal motivation. These findings suggest that both conditions promoted learners’ thinking, albeit from different perspectives: the proposed condition appeared to encourage clarification of problem-setting, whereas the Active Listening Only condition seemed to stimulate reflection on personal motivation. Future work should therefore analyze in detail how each dialogue strategy supports deeper thinking from these different perspectives.

We study whether linguistic synchrony in transcripts of Japanese speed-dating dialogues relates to willingness to exchange contact information, and whether it can be used to model this outcome. The outcome is a binary, self-reported label indicating whether the evaluator said they would like to exchange contact information with their partner immediately after the speed-dating, analyzed separately for female-to-male and male-to-female evaluations.  Building on prior findings that language style matching (LSM) tracks social cohesion and task performance, we hypothesized that greater synchrony would align with willingness to exchange contact information and improve predictive accuracy. We operationalize LSM as stylistic similarity in function-word use (particles, auxiliary verbs, pronouns, conjunctions, etc.): we compute a similarity score for each category and average across categories, yielding one LSM value per dialogue. To move beyond a global summary, we add a directional, response-side synchrony that compares a responder to the immediately preceding partner turn (rLSM), and a rolling-window rLSM(rw.rLSM) that aggregates short windows before computing rLSM to stabilize short turns and highlight local bursts of alignment. All measurements use the LIWC 2015 Japanese dictionary.  Analytically, we run two-sample, two-sided Welch’s t-tests within each rater direction, comparing conversations whose evaluators answered “yes” versus “no” to “Would you like to exchange contact information?” In female-to-male evaluations, the willing group exhibited lower synchrony on several response-side and short-window measures; this suggests that not over-matching may be positively received. In male-to-female evaluations, we observe no clear differences.  For prediction, we train separate L2-regularized logistic-regression classifiers by rater direction to classify “would exchange” vs. “would not exchange” from language-only synchrony features, using rater-held-out cross-validation with macro-F1-based thresholding. We observe near-chance performance, indicating that synchrony alone is insufficient and motivating semantic alignment and multimodal extensions.

Currently, a wide variety of visually designed social robots are being developed:  Some are closely human-like designs,  and others are human-unlike designs.　The latter includes minimal-design robots, which are designed by eliminating unnecessary functions and decorative elements as much as possible. Minimal-design robots have some advantages that they are less susceptible to issues inducing the communication failure, such as the adaptation gap and the uncanny valley effect, which are the problems that human-like robots usually confront. On the other hand, the minimal-design robots have some disadvantages that they are difficult to convey emotions effectively due to their lack of facial expression, whereas the  human-like appearance robots can produce facial expressions by moving facial components. To address this challenge, we propose a method to make minimal-design robots express their emotional valences (i.e., positive/negative emotions), inspired by studies about Noh masks, which revealed that the perceived impression of the mask changes depending on the shading. Since a Noh mask has facial parts but lacks movement, we think that the insights can be applied to a minimal-design robot.  In this study, we examine whether and how the shading influences the impressions in minimal-design robots’ faces. We employ a robot with one camera embedded on a spherical face. To generate and manipulate the shading, we arrange six light sources in front of the robot: three positioned above and three below the frontal axis, and all equidistant from the center of the sphere. For each lighting condition, we generate one image of the shaded robot. In the experiment, we plan to ask participants to view each image and rate the impression with a seven-point positive–negative scale. Based on the experimental results, we discuss the possible effectiveness and applications  of expressing emotions in minimal-design robots with shading.

This paper explores a novel interaction paradigm where an expressive Augmented Reality (AR) avatar is physically embodied by a concealed robotic arm, enabling it to manipulate real-world objects. The central challenge in making this paradigm viable is maintaining the user’s sense of presence by ensuring the actuator remains completely concealed. We designed a new interaction system and propose a key occlusion algorithm that effectively conceal the physical robotic arm from view, allowing users to perceive only the expressive virtual avatar. This approach demonstrates the potential of a new Human-Robot Interaction paradigm and opens up possibilities for everyday service robots, educational applications, and remote presence systems where low-host and highly customizable expressiveness is essential.

This presentation explores a robot-mediated approach to facilitate remote reminiscence conversations between two people in different locations. Reminiscence therapy has been widely used to help older adults recall personal memories through conversation, yet most existing methods require participants to be in the same physical space. To address this limitation, we developed a remote conversation support system that utilizes a shoulder-mounted robot to share live outdoor video with a remote participant in real time. The system integrates a large language model  that generates context-aware questions based on both the captured scene and the conversation flow, following the principles of reminiscence therapy. This enables the remote therapy recipient to engage in natural, memory-triggering dialogue, as if visiting the place together with the local companion. To evaluate the system, we conducted an experiment comparing three conditions: (1) facilitation with reminiscence-based question generation, (2) facilitation without reminiscence prompts, and (3) no facilitation. The results showed that facilitation support encouraged more active and continuous conversations, and that the reminiscence-based approach effectively enhanced memory recall for the remote participant. This study contributes to understanding how robot-mediated dialogue systems can support remote interpersonal communication, reduce barriers to social connection, and promote cognitive engagement in aging and therapeutic contexts.

Maintaining focus during web-based learning poses a significant challenge for learners, as they are constantly exposed to distracting, goal-irrelevant information sources. This study examines how the semantic context of accessed content influences the preservation or disruption of goal-directed behavior in digital environments. To address this issue, we developed an analysis framework that monitors browsing behavior by capturing the semantics of observed content. In an experiment with university students performing online research tasks, we tracked browsing sequences and extracted semantic embeddings of observed web materials using CLIP. Our method evaluates two types of similarity scores: (1) between the materials and the task objective, reflecting goal-oriented interest, and (2) between consecutive materials, capturing whether learners sustain focus or drift away from assigned goals. Quantitative analyses demonstrated that the proposed method can capture diverse patterns of interest dynamics. We also confirmed that similarity scores for relevant task–material pairs were significantly higher than those for irrelevant pairs used as a baseline (p < 0.01), highlighting the framework's ability to detect interest fluctuations. A notable strength of this method is that it relies solely on observed browsing materials without requiring special devices to infer internal cognitive states. This characteristic provides a computationally efficient approach to understanding and supporting sustained engagement in digital learning. Future applications include adaptive support systems that dynamically respond to learners' cognitive states, offering timely task recommendations to mitigate attention drift and enhance task persistence.

Emotions evolved to facilitate quick decision-making for survival and significantly influence the formation and maintenance of cooperation. Recently, artifacts that recognize and express emotion have been developed. However, the impact of artificial emotions on human cooperation is not well understood. To address this issue, this study uses cognitive modeling to simulate the role of emotions in cooperative behavior. We adopted the two-player version of "Hanabi" as a microworld to instantiate cooperative situations and incorporated the effects of emotions into instance-based learning within the ACT-R cognitive architecture. Specifically, emotional valence was modeled as a mood-congruency effect and arousal as a memory activation modulator. Additionally, we implemented decision-making that bypasses the instance-based process as heuristics to represent situations in which cooperative protocols are institutionalized. In the simulations, we manipulated task difficulty, emotional conditions (positive, neutral, negative, and dynamically fluctuating), and the degree of institutionalization. The results showed that when institutionalization was low, emotions negatively influenced performance, especially under positive conditions with high task difficulty. In these conditions, a decrease in performance due to repeated interactions was observed. In contrast, when the level of institutionalization was high, the influence of emotions was limited. Furthermore, improvement in cooperative performance through repeated interaction was observed under the neutral condition when emotions fluctuated in response to environmental feedback. In conclusion, we demonstrated that the role of emotion in cooperative behavior depends on the type of situation and that dynamic emotional adjustment contributes to the success of cooperation. At the same time, we identified a mechanism through which institutionalized heuristics suppress risk-seeking behavior driven by positive emotional conformity. These findings are important for designing artificial emotional systems that cooperate with humans.

Large Language Models (LLMs) have achieved remarkable progress in recent years. However, LLMs often show low performance in complex communications that require them to infer the hidden utterance intention of the partner. To improve the LLMs’ performances in these types of communications, we proposed LLM-based agents by integrating the LLMs with the Mental Model of Others (MMO). In this research, the MMO is defined as one of the cognitive models designed to predict and interpret the intentions of others. The evaluation results showed that our proposed agents generated appropriate utterances as if inferring the partner’s intentions. To advance this research topic further, we focused on two challenges in the study described above and investigated them in the follow-up studies. First, because the evaluations were conducted via a WebUI, we did not systematically examine the influence of sampling parameters, such as Temperature and Top_P. Our follow-up study manipulated these parameters and presented that our proposed agents robustly showed high performances regardless of these parameters. Second, because the agents’ performances were evaluated by a human evaluator, we have concerns about  the maintenance of intra-rater consistency when the very large number of the cases should be evaluated. Another follow-up study examined whether a LLM can evaluate the generated utterances in the same way as human evaluators, demonstrating that the evaluations of the LLM and the human evaluator were similar. In summary, we suggested the effectiveness and robustness of the LLM-based agents by integrating LLMs and MMOs in communication tasks requiring the inference of hidden intentions, and implied the feasibility of the evaluation of the agents’ performances by LLMs.