Freeform Preference Learning for Robotic Manipulation

Researchers propose Freeform Preference Learning (FPL), a method enabling robots to learn manipulation policies from natural-language human feedback on specific preference axes like safety or speed, addressing sparse reward issues in long-horizon tasks.

One continuously updated timeline instead of dozens of separate articles. New developments are appended as the story evolves.

1. AnnouncementJun 30, 2026, 05:54 PM 84%

   Freeform Preference Learning (FPL) introduced to improve robotic manipulation via natural-language human feedback

   Researchers propose Freeform Preference Learning (FPL), a method enabling robots to learn manipulation policies from natural-language human feedback on specific preference axes like safety or speed, addressing sparse reward issues in long-horizon tasks.

   Read the full story →