Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917066023370752 |
|---|---|
| author | Inoue, Yuichi Misaki, Kou Imajuku, Yuki Kuroki, So Nakamura, Taishi Akiba, Takuya |
| author_facet | Inoue, Yuichi Misaki, Kou Imajuku, Yuki Kuroki, So Nakamura, Taishi Akiba, Takuya |
| contents | Recent advances demonstrate that increasing inference-time computation can significantly boost the reasoning capabilities of large language models (LLMs). Although repeated sampling (i.e., generating multiple candidate outputs) is a highly effective strategy, it does not leverage external feedback signals for refinement, which are often available in tasks like coding. In this work, we propose Adaptive Branching Monte Carlo Tree Search (AB-MCTS), a novel inference-time framework that generalizes repeated sampling with principled multi-turn exploration and exploitation. At each node in the search tree, AB-MCTS dynamically decides whether to "go wider" by expanding new candidate responses or "go deeper" by revisiting existing ones based on external feedback signals. We evaluate our method on complex coding and engineering tasks using frontier models. Empirical results show that AB-MCTS consistently outperforms both repeated sampling and standard MCTS, underscoring the importance of combining the response diversity of LLMs with multi-turn solution refinement for effective inference-time scaling. Code is available at https://github.com/SakanaAI/treequest . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04412 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search Inoue, Yuichi Misaki, Kou Imajuku, Yuki Kuroki, So Nakamura, Taishi Akiba, Takuya Artificial Intelligence Recent advances demonstrate that increasing inference-time computation can significantly boost the reasoning capabilities of large language models (LLMs). Although repeated sampling (i.e., generating multiple candidate outputs) is a highly effective strategy, it does not leverage external feedback signals for refinement, which are often available in tasks like coding. In this work, we propose Adaptive Branching Monte Carlo Tree Search (AB-MCTS), a novel inference-time framework that generalizes repeated sampling with principled multi-turn exploration and exploitation. At each node in the search tree, AB-MCTS dynamically decides whether to "go wider" by expanding new candidate responses or "go deeper" by revisiting existing ones based on external feedback signals. We evaluate our method on complex coding and engineering tasks using frontier models. Empirical results show that AB-MCTS consistently outperforms both repeated sampling and standard MCTS, underscoring the importance of combining the response diversity of LLMs with multi-turn solution refinement for effective inference-time scaling. Code is available at https://github.com/SakanaAI/treequest . |
| title | Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2503.04412 |