# Deriving Character Logic from Storyline as Codified Decision Trees

arXiv: https://arxiv.org/abs/2601.10080 · HTML: https://mlsanity.com/paper/2601.10080/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023)
- [Statler: State-Maintaining Language Models for Embodied Reasoning](https://mlsanity.com/paper/2306.17840/) (2023)
- [Learning to Reason for Long-Form Story Generation](https://mlsanity.com/paper/2503.22828/) (2025)
- [LARP: Language-Agent Role Play for Open-World Games](https://mlsanity.com/paper/2312.17653/) (2023)
- [SweetieChat: A Strategy-Enhanced Role-playing Framework for Diverse Scenarios Handling Emotional Support Agent](https://mlsanity.com/paper/2412.08389/) (2024)
- [Identity-Driven Hierarchical Role-Playing Agents](https://mlsanity.com/paper/2407.19412/) (2024)
- [Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing](https://mlsanity.com/paper/2405.07726/) (2024)
- [Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning](https://mlsanity.com/paper/2506.01748/) (2025)
- [RPGBENCH: Evaluating Large Language Models as Role-Playing Game Engines](https://mlsanity.com/paper/2502.00595/) (2025)
- [Grounded Answers for Multi-agent Decision-making Problem through Generative World Model](https://mlsanity.com/paper/2410.02664/) (2024)
- [Can Large Language Models Help Developers with Robotic Finite State Machine Modification?](https://mlsanity.com/paper/2412.05625/) (2024)
- [Codifying Character Logic in Role-Playing](https://mlsanity.com/paper/2505.07705/) (2025)
- [PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs](https://mlsanity.com/paper/2505.12814/) (2025)

## Built on by (most cited first, 3 of 3)

- [Simulating Organized Group Behavior: New Framework, Benchmark, and Analysis](https://mlsanity.com/paper/2604.09874/) (2026)
- [BOOKMARKS: Efficient Active Storyline Memory for Role-playing](https://mlsanity.com/paper/2605.14169/) (2026)
- [CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents](https://mlsanity.com/paper/2605.25511/) (2026)

## Abstract (arXiv)

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.