SOURCE-LINKED INTELLIGENCE

Efficient Test-Time Adaptation through Human-AI Interaction

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

AI agents are trained on population-scale data to encode broad capabilities spanning those of many practitioners. Yet the artifacts they produce rarely meet the personal bar professionals need to stake their reputation on. On realistic, open-ended tasks where success criteria are heterogeneous and insufficiently documented, individual expertise lives precisely in the elevation and departure from the average. In practice, iterative human-agent interaction surfaces criteria that users cannot fully specify up front, yet apply repeatedly across tasks. We argue this cross-session interaction data i

Read original source ↗ Open in workspace

recordType

paper

region

Global