When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models

2026-08-31

AI Summary

本文探讨了通过树搜索方法改进大型语言模型推理问题，从单一轨迹解码转向基于实例的优化，并提出了统一设计空间。

Abstract

As pretraining scaling laws approach saturation, Test-Time Scaling (TTS) has emerged as an important direction for improving reasoning by allocating inference-time compute to a fixed model prior. Viewed at a high level, TTS reframes inference as search over a space of partial reasoning states. While Chain-of-Thought (CoT) exposes intermediate steps, common instantiations rely on single-trajectory decoding, limiting recovery from early errors and exploration. This survey systematizes recent progress in tree-search-based reasoning, viewing inference as instance-specific optimization rather than decoding. We trace the evolution from uninformed search to Monte Carlo Tree Search (MCTS), highlighting how sampling-based control supports principled exploration-exploitation trade-offs. To unify a fragmented literature, we introduce a Unified Design Space spanning search topology, evaluation signals, and control dynamics, and advocate a standardized compute-reporting abstraction to make compute-accuracy trade-offs explicit and comparable.

Problem

• Test-Time Scaling
• Chain-of-Thought
• Tree Search

Innovation

• Tree Search
• Inference as Search
• Unified Design Space
• Compute-accuracy Trade-offs