The Consent Vacuum: When Agents Interact Without Humans
Existing consent frameworks assume a human who authorises an action in a context they can see.
Existing consent frameworks assume a human who authorises an action in a context they can see.
Extends Guided Soft Actor-Critic with Belief-Aware GSAC, which scales the privileged-distillation coefficient by ensemble disagreement in a driving POMDP.
Introduces consent chain degradation: the way the specificity, validity and scope of human consent weaken as authority passes through chains of delegation among embodied agents.
Presents TR-TEB, a standardized and reproducible benchmark for Turkish text embeddings.
A position paper on why consent mechanisms designed for conversational systems fail once AI moves from answering to acting on a user's behalf.
Research area: Agentic AI Safety & Governance.
Research area: AI for Geoscience & Energy.
Research area: Language Technologies & LLMs, Computer Vision & Applied AI.
Research area: AI for Geoscience & Energy, Reinforcement Learning & Autonomous Systems.
Research area: AI for Geoscience & Energy.