The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
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:2607. 18257v1 Announce Type: cross Abstract: When AI agents shift from answering questions to taking actions, users face a new problem: deciding what to delegate, to a system whose action space they cannot fully anticipate.
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.
Machine learning-based Intrusion Detection Systems (IDS) have demonstrated superior performance in securing Unmanned Aerial Vehicle (UAV) networks. However, the 'black-box' nature of these models, combined with the high dimensionality of multimodal cyber-physical data, poses significant interpretability challenges.
arXiv:2608. 10434v1 Announce Type: new Abstract: Machine learning-based Intrusion Detection Systems (IDS) have demonstrated superior performance in securing Unmanned Aerial Vehicle (UAV) networks.
arXiv:2611.03092v1 Announce Type: cross Abstract: Personal AI agents are increasingly capable of handling long-horizon tasks across applications, yet users often need to invest substantial effort in...