RULER (Relative Universal LLM-Elicited Rewards) eliminates the need for hand-crafted reward functions by using an LLM-as-judge to automatically score agent trajectories. Simply define your task in the ...
My friend passed away some weeks ago and left $25,000 to her son, who is now in his 20s, and envelopes of $300 to her closest friends. While she was very sick in hospice care, her brother took this ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback