Causal discovery aims to recover ``what causes what'', but classical constraint-based methods (e.g., PC, FCI) suffer from error propagation, and recent LLM-based causal oracles often behave as opaque, confidence-free black boxes. This paper introduces Tree-Query, a tree-structured, multi-expert LLM framework that reduces pairwise causal discovery to a short sequence of queries about backdoor paths, (in)dependence, latent confounding, and causal direction, yielding interpretable judgments with robustness-aware confidence scores. Theoretical guarantees are provided for asymptotic identifiability of four pairwise relations. On data-free benchmarks derived from Mooij et al. and UCI causal graphs, Tree-Query improves structural metrics over direct LLM baselines, and a diet--weight case study illustrates confounder screening and stable, high-confidence causal conclusions. Tree-Query thus offers a principled way to obtain data-free causal priors from LLMs that can complement downstream data-driven causal discovery. Code is available at https://anonymous.4open.science/r/Repo-9B3E-4F96.

翻译：因果发现旨在揭示“何因导致何果”，但经典的基于约束的方法（如PC、FCI）存在误差传播问题，而近期基于大语言模型（LLM）的因果预测器往往表现为不透明、无置信度评估的黑箱。本文提出Tree-Query，一种树状结构的多专家LLM框架，它将成对因果发现简化为关于后门路径、（非）独立性、潜在混杂因素和因果方向的短序列查询，从而生成可解释的判断并附带鲁棒性感知的置信度评分。该框架为四种成对关系的渐近可识别性提供了理论保证。在基于Mooij等人及UCI因果图构建的无数据基准测试中，Tree-Query在结构度量上优于直接的LLM基线方法；一项关于饮食与体重的案例研究展示了其混杂因素筛查能力及稳定、高置信度的因果结论。因此，Tree-Query提供了一种从LLM中获取无数据因果先验的原则性方法，可补充下游数据驱动的因果发现。代码发布于 https://anonymous.4open.science/r/Repo-9B3E-4F96。