Re:Tree Search Distillation for Language Models Using PPO
by natufunu on Sunday March 15, 2026 @02:20AM
(#47384806)
Great post! I wonder why MCTS is not more popular as a test time compute harness. Did you compare performance of MCTS (without distillation) against other methods (eg best of N) with the same compute budget?
[ Parent
| on HN ]
Re:Tree Search Distillation for Language Models Using PPO
by at2005 on Monday March 16, 2026 @05:47PM
(#47405396)
I didn't compare with the harness (focused on distillation) but the original ToT paper has a section on it: https://arxiv.org/abs/2305.10601