用大模型直接解释蒙特卡洛树搜索决策，无需人工设计规则。
Toward Template-Free Explainability for Monte Carlo Tree Search
- 大模型直接分析搜索轨迹生成解释，无需中间形式化表示。
- 根据访问次数、价值估计等数据判断是否需扩展搜索树。
- 适合需要理解复杂决策过程的研究者与开发者。
概率搜索算法如蒙特卡洛树搜索（MCTS）在不确定性下的序列决策任务中表现优异。然而，仅凭原始树统计信息，用户难以理解包含基于赌徒策略的遍历和基于模拟的价值估计的非对称搜索树。以往方法依赖人工设计的逻辑约束，问题变化时需重新调整。本文提出一个框架，使大语言模型（LLMs）能从记录的搜索轨迹中端到端生成基于证据的MCTS决策解释。该框架将自然语言问题映射为意图类别，判断现有树结构是否具备足够证据，必要时触发针对性扩展，并利用访问次数、价值估计及风险信息生成解释。实验首次表明，大模型可在无需中间形式表示的情况下，作为概率搜索的端到端解释器。
原文摘要 · Abstract (English)
Probabilistic search algorithms, such as Monte Carlo Tree Search (MCTS), have proven very effective in solving sequential decision-making tasks under uncertainty. However, interpreting asymmetric search trees that incorporate bandit-based tree traversal and simulation-based value estimation is difficult for end users based solely on raw tree statistics. While prior work requires hand-crafted formal logic constraints that must be updated when the problem changes, we present a framework that enables large language models (LLMs) to generate evidence-grounded explanations of MCTS decisions from recorded search traces in an end-to-end manner. Our framework maps natural-language questions to a structured set of intent categories, determines whether the existing tree contains sufficient evidence, triggers targeted expansion when needed, and generates explanations using tree statistics such as visit counts, value estimates, and risk information. Experimental results provide the first evidence that LLMs can serve as end-to-end explainers for probabilistic search, without requiring intermediate formal representations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。