The study examines how proactive in‑cabin agents should communicate in fully automated vehicles, comparing an event‑triggered policy that speaks at every event with a context‑sensitive policy that chooses Immediate, Delayed, or Silent responses. In a VR simulation with 41 participants, the context‑sensitive approach improved communication appropriateness and significantly lowered perceived interruptions, while trust levels remained unchanged. The results emphasize that event consequence, passenger activity, ongoing information value, and the need for confirmation should guide selective in‑cabin communication.
arXiv:2607. 17701v1 Announce Type: new Abstract: Proactive agents are expected to anticipate user needs and provide autonomous assistance by perceiving environmental context without explicit instructions.
arXiv:2608.21841v1 Announce Type: new Abstract: Conversational AI increasingly shapes consequential decisions, yet users have limited support for recognizing and resisting manipulation. We present AI...
arXiv:2602.17850v2 Announce Type: replace-cross Abstract: Conversational agents increasingly mediate everyday digital interactions, yet the effects of their communication style on user experience and...
arXiv:2606. 14314v1 Announce Type: new Abstract: LLM agents have rapidly evolved into autonomous systems, yet a persistent information gap remains between users and agents: communication is costly, while users' identical preferences further limit information exchange.
DuplexSpeechBench-IFEval (DSB-IFEval) is a new benchmark that evaluates how full‑duplex voice agents follow implicit instructions during real‑time spoken interaction. It contains 1,038 test cases across eight assistant roles and tests five conditioning protocols, measuring floor management with an Instruction Adherence Score (IAS) and persona consistency with a Persona Adherence Score (PAS). Experiments on six speech systems reveal architecture‑dependent trade‑offs, showing that some models are more sensitive to explicit versus persona‑only instructions and that even when following conflicting directives, they struggle to override them under safety conflict.
arXiv:2610.20172v1 Announce Type: cross Abstract: Full-duplex speech systems must decide when to enter, hold, or relinquish the conversational floor, even as multiple speakers overlap or backchannel...
arXiv:2606. 03137v1 Announce Type: new Abstract: LLM-based multi-agent simulation offers a promising way to study social interaction, deliberation, and collective opinion dynamics.
The study investigates how verbal attunement and real‑time behavioral mimicry affect users’ perceptions of an embodied AI counselor in virtual reality. Participants interacted with a system that varied in verbal attunement (attuned vs. neutral) and behavioral mimicry (present vs. absent). Results indicated that verbal attunement most reliably increased perceived empathy, while mimicry had a marginal effect on perceived humanness and showed exploratory positive associations with empathy, positivity, and humanness, especially among female participants.
SecondVoice is a mixed‑reality system that lets participants speak up in co‑located discussions via an embodied virtual proxy, separating the content of a point from the speaker’s identity. Users input their intent through a structured process, and the system reformulates and vocalizes it into the conversation. In a study with 16 participants, the proxy channel led to more points being voiced than an anonymous text board and sparked multi‑turn engagement that the text board did not elicit.
arXiv:2607. 24761v1 Announce Type: cross Abstract: Research on human-AI interaction has long framed verification of system outputs as a trust-contingent behavior that better-calibrated trust should reduce.
The study examined how users delegate control to multimodal AI by analyzing 392 video question‑answering trials with 56 AI‑literate participants. Participants rated trust after each AI response and chose one of three delegation policies—reject, verify, or fully delegate. Findings showed that higher post‑interaction trust predicted delegation choices, verification was the most common policy, and delegation increased with task order, suggesting experience influences trust beyond self‑reported ratings.
arXiv:2606. 18258v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit a wide range of human-like behaviors, from expressing thoughts and emotions, to engaging in relationship-building with users, to refusing requests and maintaining boundaries.