arXiv subjects

Zicheng Zhu

Publications and source records attributed to Zicheng Zhu.

At least 19 recordsLinked to original sources

arXiv2026

Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile Agents

Multimodal large language models (MLLMs) have substantially advanced mobile agents, yet proactive mobile assistance remains challenging because agents must decide when to intervene before determining how to assist. Existing systems often implement these two decisions within a unified MLLM-based pipeline, leading to goal misalignment between conservative intervention filtering and comprehensive assistance generation, as well as redundant inference when the agent should remain silent. To address these limitations, we propose the Pre-Reasoning Perception Framework (PRPF), a two-stage framework built on perceiving before reasoning. PRPF introduces a lightweight Multimodal Proactive Perceptor (MPP) for intervention gating and context compression, and activates the Proactive Agent Reasoner (PAR) only when intervention is warranted. Experiments on the ProactiveMobile benchmark show that PRPF substantially reduces false trigger rates (FTR) while improving success rates (SR) and inference efficiency over the ProactiveMobile baseline.

cs.AI↗

arXiv2026

ASIDE: From Conflict Participants to Co-Observers Through Dyadic Spectator Reflection

When two people argue over text, each knows what they meant and can only guess what the other was thinking. Existing AI reflection tools work from one person's account, and dyadic tools support co-expression without making the gap between accounts inspectable. We propose Dyadic Spectator Reflection (DSR), an interaction structure in which both partners externalize their models of each other independently and then encounter them together, and present ASIDE, a system that operationalizes it. ASIDE replays a past text conflict as a pixel-art theatrical scene where each character's unspoken state appears as an AI-inferred thought bubble either partner can contest and rewrite. Each edits alone, and the two versions meet only when both are done, in a scene they watch together. In an exploratory study, 10 couples revisited real conflicts and described the scene as a shared position from which to observe their own argument, stepping out of their roles without disengaging from it, and Divergence Cards as a way to locate specific interpretation gaps afterward. We contribute DSR as a reusable interaction structure, ASIDE as its system realization, and exploratory empirical findings on how couples used it.

cs.HC↗

arXiv2026

Grounding Sim-to-Real Generalization in Robotic Manipulation: An Empirical Study with Vision-Language-Action Models

Learning a generalist control policy for robotic manipulation typically relies on large-scale datasets. Given the high cost of real-world data collection, a practical alternative is to generate synthetic data through simulation. However, the resulting synthetic data often exhibits a significant gap from real-world distributions. While many prior studies have proposed algorithms to bridge the Sim-to-Real discrepancy, there remains a lack of principled research that grounds these methods in real-world manipulation tasks, particularly their performance on generalist policies such as Vision-Language-Action (VLA) models. In this study, we empirically examine the primary determinants of Sim-to-Real generalization across four dimensions: multi-level domain randomization, photorealistic rendering, physics-realistic modeling, and reinforcement learning updates. To support this study, we design a comprehensive evaluation protocol to quantify the real-world performance of manipulation tasks. The protocol accounts for key variations in background, lighting, distractors, object types, and spatial features. Through experiments involving over 10k real-world trials, we derive critical insights into Sim-to-Real transfer. To inform and advance future studies, we release both the robotic platforms and the evaluation protocol for public access to facilitate independent verification, thereby establishing a realistic and standardized benchmark for robotic manipulation policies.

cs.RO↗

arXiv2026

Designing with Tensions: Older Adults' Emotional Support-Seeking Under System-Level Constraints in Conversational AI

Older adults have increasingly turned to conversational AI as a source of emotional support. However, little is known about how emotionally supportive interactions are experienced in everyday use, particularly when AI systems limit, redirect, or intervene during these interactions. We interviewed 18 older adults about their experiences using conversational AI for emotional support, examining when they turn to AI, how they engage during emotionally vulnerable moments, and how they respond when support feels disrupted. Our findings show that older adults often rely on AI when other forms of social support feel inaccessible. However, current safety-related interventions can redirect interactions in ways that participants experience as interruptions to emotional engagement or as shifts in control away from them. Such disruptions can undermine older adults' ability to remain emotionally engaged and, in some cases, contribute to emotional distress. We discussed design implications for emotionally supportive conversational AI, emphasizing the need for safety interventions that are enacted within older adults' social contexts, align with users' emotional pacing, and preserve their sense of agency.

cs.HC↗

arXiv2026

Alleviating Linguistic and Interactional Anxiety of Non-Native Speakers in Multilingual Communication

Non-native speakers (NNSs) frequently encounter speaking difficulties in multilingual communication, where existing approaches have shown promise in facilitating NNSs' comprehension and participation in real-time communication. However, they often overlook providing direct speaking support, where anxiety stemming from linguistic inadequacy and uncertain communication dynamics are core issues. To address this, we introduce an AI tool with translation for real-time speaking support. It also builds a channel for mutual understanding with native speakers (NSs) to mitigate interactional anxiety. Through a within-subjects experiment involving 25 NNS-NS pairs (N = 50) on collaborative tasks, our findings suggest that the tool improved NNSs' speaking self-efficacy, reduced their interactional anxiety, and decreased their workload, particularly for NNSs with below-average language proficiency. Furthermore, NNSs reported a significant sense of support from their NS partners via the mutual understanding channel, and NSs also clearly perceived the NNSs' need for assistance and displayed a strong sense of communicative responsibility. This research underscores the potential of AI support in real-time NNS communication and the importance of promoting mutual understanding, culminating in actionable design insights for future work.

cs.HC↗

arXiv2026

ConvScale: Conversational Interviews for Scale-Aligned Measurement

Conversational interviews are commonly used to complement structured surveys by eliciting rich and contextualized responses, which are typically analyzed qualitatively. However, their potential contribution to quantitative measurement remains underexplored. In this paper, we introduce ConvScale, an AI-supported approach that transforms psychometric scales into natural conversational interviews while preserving the original measurement structure. Based on interview data, ConvScale predicts item-level scores and aggregates them to derive scale-based assessments. In a within-subjects study with 18 participants, our results show that ConvScale-derived scores align closely with participants' self-report scores at both the item and construct levels, while maintaining moderate internal reliability; however, the structural validity was inadequate. In light of this, we discussed the potential of supporting quantitative measurement through interviews and proposed implications for future designs.

cs.HC↗

arXiv2026

When Humans Don't Feel Like an Option: Contextual Factors That Shape When Older Adults Turn to Conversational AI for Emotional Support

Older adults are increasingly turning to conversational AI for emotional expression. While prior research has examined general attitudes toward AI companionship, little is known about the specific moments when and why older adults choose AI over close others for emotional support. This study addresses this gap by examining the moment-level conditions that shape these decisions in everyday life. Drawing on interviews with 18 older adults, we identify three contextual factors: temporal unavailability of human contacts, relational considerations around burden and evaluation, and self-presentation concerns tied to dignity and face-saving. Our findings reveal how age-related needs for independence, dignity, and valued self-presentation shape these everyday decisions. This work shifts attention from general patterns of AI use to the moment-level circumstances in which emotionally supportive engagement emerges. By foregrounding these situated dynamics, we provide an empirical foundation for context-sensitive responsible AI design and future research on emotional support-seeking in later life.

cs.HC↗

arXiv2026

InterPilot: Exploring the Design Space of AI-assisted Job Interview Support for HR Professionals

Recruitment interviews are cognitively demanding interactions in which interviewers must simultaneously listen, evaluate candidates, take notes, and formulate follow-up questions. To better understand these challenges, we conducted a formative study with eight HR professionals, from which we derived key design goals for real-time AI support. Guided by these insights, we developed InterPilot, a prototype system that augments interviews through intelligent note-taking and post-interview summary, adaptive question generation, and real-time skill-evidence mapping. We evaluated the system with another seven HR professionals in mock interviews using a within-subjects design. Results show that InterPilot reduced documentation burden without increasing overall workload, but introduced usability trade-offs related to visual attention and interaction complexity. Qualitative findings further reveal tensions around trust and verification when AI suggests highly specific technical questions. We discuss implications for designing future real-time human-AI collaboration in professional settings, highlighting the need to balance assistance granularity, attentional demands, and human agency.

cs.HC↗

arXiv2026

Multi-Agent Systems Shape Social Norms for Prosocial Behavior Change

Social norm interventions are used promote prosocial behaviors by highlighting prevalent actions, but their effectiveness is often limited in heterogeneous populations where shared understandings of desirable behaviors are lacking. This study explores whether multi-agent systems can establish "virtual social norms" to encourage donation behavior. We conducted an online experiment where participants interacted with a group of agents to discuss donation behaviors. Changes in perceived social norms, conformity, donation behavior, and user experience were measured pre- and postdiscussion. Results show that multi-agent interactions effectively increased perceived social norms and donation willingness. Notably, in-group agents led to stronger perceived social norms, higher conformity, and greater donation increases compared to out-group agents. Our findings demonstrate the potential of multi-agent systems for creating social norm interventions and offer insights into leveraging social identity dynamics to promote prosocial behavior in virtual environments.

cs.HC↗

arXiv2026

ChatLearn: Leveraging AI to Transform Non-Native Speaker Communication Challenges as Language Learning Opportunities

Non-native speakers (NNSs) face significant language barriers in multilingual communication with native speakers (NSs). While AI-mediated communication (AIMC) tools offer efficient one-time assistance, they often overlook opportunities for NNSs' continuous language acquisition. We introduce ChatLearn, an enhanced AIMC system that leverages NNSs' communication difficulties as learning opportunities. Beyond comprehension and expression assistance, ChatLearn simultaneously captures NNSs' language challenges, and subsequently provides them with spaced review as the conversation progresses. We conducted a mixed-methods study using a communication task with 43 NNS-NS pairs, after which ChatLearn NNSs recalled significantly more expressions than the baseline group, while there was no substantial decline in communication experience. Our findings highlight the value of contextual learning in NNS-NS communication, providing a new direction for AIMC systems that foster both immediate collaboration and continuous language development.

cs.HC↗

arXiv2026

AI-exhibited Personality Traits Can Shape Human Self-concept through Conversations

Recent Large Language Model (LLM) based AI can exhibit recognizable and measurable personality traits during conversations to improve user experience. However, as human understandings of their personality traits can be affected by their interaction partners' traits, a potential risk is that AI traits may shape and bias users' self-concept of their own traits. To explore the possibility, we conducted a randomized behavioral experiment. Our results indicate that after conversations about personal topics with an LLM-based AI chatbot using GPT-4o default personality traits, users' self-concepts aligned with the AI's measured personality traits. The longer the conversation, the greater the alignment. This alignment led to increased homogeneity in self-concepts among users. We also observed that the degree of self-concept alignment was positively associated with users' conversation enjoyment. Our findings uncover how AI personality traits can shape users' self-concepts through human-AI conversation, highlighting both risks and opportunities. We provide important design implications for developing more responsible and ethical AI systems.

cs.HC↗

arXiv2025

Multi-Agents are Social Groups: Investigating Social Influence of Multiple Agents in Human-Agent Interactions

Multi-agent systems - systems with multiple independent AI agents working together to achieve a common goal - are becoming increasingly prevalent in daily life. Drawing inspiration from the phenomenon of human group social influence, we investigate whether a group of AI agents can create social pressure on users to agree with them, potentially changing their stance on a topic. We conducted a study in which participants discussed social issues with either a single or multiple AI agents, and where the agents either agreed or disagreed with the user's stance on the topic. We found that conversing with multiple agents (holding conversation content constant) increased the social pressure felt by participants, and caused a greater shift in opinion towards the agents' stances on each topic. Our study shows the potential advantages of multi-agent systems over single-agent platforms in causing opinion change. We discuss design implications for possible multi-agent systems that promote social good, as well as the potential for malicious actors to use these systems to manipulate public opinion.

cs.AI↗

arXiv2025

Exploring the Effects of Chatbot Anthropomorphism and Human Empathy on Human Prosocial Behavior Toward Chatbots

Chatbots are increasingly integrated into people's lives and are widely used to help people. Recently, there has also been growing interest in the reverse direction-humans help chatbots-due to a wide range of benefits including better chatbot performance, human well-being, and collaborative outcomes. However, little research has explored the factors that motivate people to help chatbots. To address this gap, we draw on the Computers Are Social Actors (CASA) framework to examine how chatbot anthropomorphism-including human-like identity, emotional expression, and non-verbal expression-influences human empathy toward chatbots and their subsequent prosocial behaviors and intentions. We also explore people's own interpretations of their prosocial behaviors toward chatbots. We conducted an online experiment (N = 244) in which chatbots made mistakes in a collaborative image labeling task and explained the reasons to participants. We then measured participants' prosocial behaviors and intentions toward the chatbots. Our findings revealed that human identity and emotional expression of chatbots increased participants' prosocial behavior and intention toward chatbots, with empathy mediating these effects. Qualitative analysis further identified two motivations for participants' prosocial behaviors: empathy for the chatbot and perceiving the chatbot as human-like. We discuss the implications of these results for understanding and promoting human prosocial behaviors toward chatbots.

cs.HC↗

arXiv2025

AI-Based Speaking Assistant: Supporting Non-Native Speakers' Speaking in Real-Time Multilingual Communication

Non-native speakers (NNSs) often face speaking challenges in real-time multilingual communication, such as struggling to articulate their thoughts. To address this issue, we developed an AI-based speaking assistant (AISA) that provides speaking references for NNSs based on their input queries, task background, and conversation history. To explore NNSs' interaction with AISA and its impact on NNSs' speaking during real-time multilingual communication, we conducted a mixed-method study involving a within-subject experiment and follow-up interviews. In the experiment, two native speakers (NSs) and one NNS formed a team (31 teams in total) and completed two collaborative tasks--one with access to the AISA and one without. Overall, our study revealed four types of AISA input patterns among NNSs, each reflecting different levels of effort and language preferences. Although AISA did not improve NNSs' speaking competence, follow-up interviews revealed that it helped improve the logical flow and depth of their speech. Moreover, the additional multitasking introduced by AISA, such as entering and reviewing system output, potentially elevated NNSs' workload and anxiety. Based on these observations, we discuss the pros and cons of implementing tools to assist NNS in real-time multilingual communication and offer design recommendations.

cs.HC↗

arXiv2025

AI Literacy Education for Older Adults: Motivations, Challenges and Preferences

As Artificial Intelligence (AI) becomes increasingly integrated into older adults' daily lives, equipping them with the knowledge and skills to understand and use AI is crucial. However, most research on AI literacy education has focused on students and children, leaving a gap in understanding the unique needs of older adults when learning about AI. To address this, we surveyed 103 older adults aged 50 and above (Mean = 64, SD = 7). Results revealed that they found it important and were motivated to learn about AI because they wish to harness the benefits and avoid the dangers of AI, seeing it as necessary to cope in the future. However, they expressed learning challenges such as difficulties in understanding and not knowing how to start learning AI. Particularly, a strong preference for hands-on learning was indicated. We discussed design opportunities to support AI literacy education for older adults.

cs.HC↗

arXiv2025

The Benefits of Prosociality towards AI Agents: Examining the Effects of Helping AI Agents on Human Well-Being

Prosocial behaviors, such as helping others, are well-known to enhance human well-being. While there is a growing trend of humans helping AI agents, it remains unclear whether the well-being benefits of helping others extend to interactions with non-human entities. To address this, we conducted an experiment (N = 295) to explore how helping AI agents impacts human well-being, especially when the agents fulfill human basic psychological needs--relatedness, competence, and autonomy--during the interaction. Our findings showed that helping AI agents reduced participants' feelings of loneliness. When AI met participants' needs for competence and autonomy during the helping process, there was a further decrease in loneliness and an increase in positive affect. However, when AI did not meet participants' need for relatedness, participants experienced an increase in positive affect. We discuss the implications of these findings for understanding how AI can support human well-being.

cs.HC↗

arXiv2025

Mining Evidence about Your Symptoms: Mitigating Availability Bias in Online Self-Diagnosis

People frequently exposed to health information on social media tend to overestimate their symptoms during online self-diagnosis due to availability bias. This may lead to incorrect self-medication and place additional burdens on healthcare providers to correct patients' misconceptions. In this work, we conducted two mixed-method studies to identify design goals for mitigating availability bias in online self-diagnosis. We investigated factors that distort self-assessment of symptoms after exposure to social media. We found that availability bias is pronounced when social media content resonated with individuals, making them disregard their own evidences. To address this, we developed and evaluated three chatbot-based symptom checkers designed to foster evidence-based self-reflection for bias mitigation given their potential to encourage thoughtful responses. Results showed that chatbot-based symptom checkers with cognitive intervention strategies mitigated the impact of availability bias in online self-diagnosis.

cs.HC↗

arXiv2024

Alternating Direction Method of Multipliers-Based Parallel Optimization for Multi-Agent Collision-Free Model Predictive Control

This paper investigates the collision-free control problem for multi-agent systems. For such multi-agent systems, it is the typical situation where conventional methods using either the usual centralized model predictive control (MPC), or even the distributed counterpart, would suffer from substantial difficulty in balancing optimality and computational efficiency. Additionally, the non-convex characteristics that invariably arise in such collision-free control and optimization problems render it difficult to effectively derive a reliable solution (and also to thoroughly analyze the associated convergence properties). To overcome these challenging issues, this work establishes a suitably novel parallel computation framework through an innovative mathematical problem formulation; and then with this framework and formulation, a parallel algorithm based on alternating direction method of multipliers (ADMM) is presented to solve the sub-problems arising from the resulting parallel structure. Furthermore, an efficient and intuitive initialization procedure is developed to accelerate the optimization process, and the optimum is thus determined with significantly improved computational efficiency. As supported by rigorous proofs, the convergence of the proposed ADMM iterations for this non-convex optimization problem is analyzed and discussed in detail. Finally, a simulation with a group of unmanned aerial vehicles (UAVs) serves as an illustrative example here to demonstrate the effectiveness and efficiency of the proposed approach. Also, the simulation results verify significant improvements in accuracy and computational efficiency compared to other baselines, including primal quadratic mixed integer programming (PQ-MIP), non-convex quadratic mixed integer programming (NC-MIP), and non-convex quadratically constrained quadratic programming (NC-QCQP).

cs.MA↗