AB-MCTS

Creator
Creator
Seonglae ChoSeonglae Cho
Created
Created
2025 Jul 5 11:57
Editor
Edited
Edited
2025 Jul 10 20:46
Refs
Refs
Alpha Go

Adaptive Branching

ARC-AGI
2 from 23 to 30

At each step, a choice is made between "creating a new answer (breadth)" vs "refining an existing answer (depth)", as well as deciding "which LLM (model) to assign the task". This selection is made using
Thompson sampling
, which considers performance history to make decisions.
Each node (answer) receives a score (Reward) based on "how well this answer solved the problem"
 
 
 
 
 

Recommendations