从剧情中推导人物逻辑：编码为决策树的方法

摘要

角色扮演（RP）智能体依赖行为配置文件在不同叙事情境中保持行为一致性，但现有配置文件大多为非结构化、不可执行且缺乏有效验证，导致智能体行为脆弱易变。我们提出编码决策树（CDT）这一数据驱动框架，能够从大规模叙事数据中归纳出可执行且可解释的决策结构。CDT将行为配置文件表示为条件规则树：内部节点对应经过验证的场景条件，叶节点编码具体行为陈述，从而在执行时实现上下文适配规则的确定性检索。该框架通过迭代归纳候选场景-动作规则、进行数据验证及层级细化来构建决策树，最终形成支持透明检视与原则性更新的配置文件。在涵盖16个叙事作品的85个角色测试中，CDT在多项基准测试上显著优于人工编写配置文件及先前的配置文件归纳方法，表明经过编码与验证的行为表征能实现更可靠的智能体行为锚定。

English

Role-playing (RP) agents rely on behavioral profiles to act consistently across diverse narrative contexts, yet existing profiles are largely unstructured, non-executable, and weakly validated, leading to brittle agent behavior. We propose Codified Decision Trees (CDT), a data-driven framework that induces an executable and interpretable decision structure from large-scale narrative data. CDT represents behavioral profiles as a tree of conditional rules, where internal nodes correspond to validated scene conditions and leaves encode grounded behavioral statements, enabling deterministic retrieval of context-appropriate rules at execution time. The tree is learned by iteratively inducing candidate scene-action rules, validating them against data, and refining them through hierarchical specialization, yielding profiles that support transparent inspection and principled updates. Across multiple benchmarks, CDT substantially outperforms human-written profiles and prior profile induction methods on 85 characters across 16 artifacts, indicating that codified and validated behavioral representations lead to more reliable agent grounding.

从剧情中推导人物逻辑：编码为决策树的方法

Deriving Character Logic from Storyline as Codified Decision Trees

摘要

Support