让大模型决策像树一样清晰可查，支持文本输入的可解释分类系统。
ACT: Agentic Classification Tree
- 将决策树的分裂逻辑转化为自然语言问题，结合大模型生成与反馈。
- 在多个文本分类基准上表现优于或媲美提示工程方法。
- 适合需要透明、可审计决策的医疗、金融等高风险场景使用。
在高风险应用中，人工智能系统需提供透明、可解释且可审计的决策，这越来越成为监管要求。传统决策树（如CART）虽具备明确可验证的规则，但仅限于结构化表格数据，无法直接处理文本等非结构化输入。实践中，大语言模型（LLMs）被广泛用于此类数据，但链式思维或提示优化等提示策略仍依赖自由形式推理，难以保障可信行为。本文提出代理分类树（ACT），通过将每个分裂节点建模为自然语言问题，并利用信息熵评估与TextGrad框架下的LLM反馈进行迭代优化，实现对非结构化输入的决策树构建。在多个文本基准上的实验表明，ACT在性能上达到或超越基于提示的基线方法，同时生成透明可解释的决策路径。
原文摘要 · Abstract (English)
When used in high-stakes settings, AI systems are expected to produce decisions that are transparent, interpretable and auditable, a requirement increasingly expected by regulations. Decision trees such as CART provide clear and verifiable rules, but they are restricted to structured tabular data and cannot operate directly on unstructured inputs such as text. In practice, large language models (LLMs) are widely used for such data, yet prompting strategies such as chain-of-thought or prompt optimization still rely on free-form reasoning, limiting their ability to ensure trustworthy behaviors. We present the Agentic Classification Tree (ACT), which extends decision-tree methodology to unstructured inputs by formulating each split as a natural-language question, refined through impurity-based evaluation and LLM feedback via TextGrad. Experiments on text benchmarks show that ACT matches or surpasses prompting-based baselines while producing transparent and interpretable decision paths.
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。