Causally Robust Reward Learning from Reason-Augmented Preference Feedback
arXiv:2603.04861v1 Announce Type: new Abstract: Preference-based reward learning is widely used for shaping agent behavior to match a user's preference, yet its sparse binary feedback …
Minjune Hwang, Yigit Korkmaz, Daniel Seita, Erdem B{\i}y{\i}k
11 views