arXiv Computer Vision By Kaiser Hamid, Peihang Li, Nade Liang

When2Talk: When Should a Proactive In-Car Agent Talk?

Read the original on arXiv Computer Vision →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI
Aug 25

AI Watchdog: Agent Interfaces for Detecting and Defending Against Manipulative Dark Patterns in AI Conversations

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...

By Rachel Poonsiriwong (Pub), Chayapatr (Pub), Archiwaranguprok, Constanze Albrecht, Monchai Lertsutthiwong, Pattie Maes, Pat Pataranutaporn
arXiv AI
Jun 15

Communication Policy Evolution for Proactive LLM Agents

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.

By Xinbei Ma, Jiyang Qiu, Yao Yao, Zheng Wu, Yijie Lu, Xiangmou Qu, Jiaxin Yin, Xingyu Lou, Jun Wang, Weiwen Liu, Weinan Zhang, Zhuosheng Zhang, Hai Zhao
arXiv AI
Sep 4

DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents

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.

By Puneet Mathur, Dinesh Manocha