用故事数据生成可执行的行为决策树，让角色扮演更可靠。
Deriving Character Logic from Storyline as Codified Decision Trees
- 从大规模叙事数据中自动构建条件规则树，结构清晰可执行。
- 在16个作品、85个角色上表现优于人工撰写和旧方法。
- 适合需要稳定角色行为的互动系统开发人员。
角色扮演（RP）代理依赖行为档案在多变的叙事情境中保持一致行为，但现有档案大多无结构、不可执行且验证不足，导致行为脆弱。我们提出编码决策树（CDT），一种基于数据驱动的框架，能从大规模叙事数据中推导出可执行且可解释的决策结构。CDT将行为档案表示为条件规则树，内部节点对应经验证的场景条件，叶节点编码具体的行动语句，实现执行时确定性地检索适配规则。该树通过迭代生成候选场景-行动规则、数据验证并分层细化来学习，得到的档案支持透明审查与规范更新。在多个基准测试中，CDT在16个作品中的85个角色上显著优于人工编写档案及以往方法，表明编码且经过验证的行为表示能带来更可靠的代理落地效果。
原文摘要 · Abstract (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.
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。