I heard about this on Twitter from some people in the field, in relation to OpenAI’s new breakthrough.
Is there a summary paper, like the ‘All you need is attention’ paper, that goes over this?
Also, how specifically does this relate to and/or add on to Large Language Models?
Cheers
You must log in or register to comment.
I assume its similar to Q learning.
The star implies its a pathfinding algorithm which Q learning already kinda is.
So, what about https://arxiv.org/pdf/2310.04406v1.pdf ? LANGUAGE AGENT TREE SEARCH UNIFIES REASONING ACTING AND PLANNING IN LANGUAGE MODELS. For me, it looks like very similar. The results are 98% on HumanEval
“All you need is attention” made me twitch my eyes a little