Timbre: Reliability-aware harmonic consensus for label-free multimodal test-time rexinforcement learning
arXiv:2610.39439v1 Announce Type: new Abstract: Label-free test-time reinforcement learning adapts vision--language models using rewards derived from their own predictions. However, misinterpreted visual evidence and sensitivity to textual formulation can produce a consistent but incorrect consensus that majority voting reinforces. Cross-view aggregation can expose such errors, but image and text transformations may themselves degrade task-relevant evidence to different extents. We introduce \m…