# CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds

arXiv: https://arxiv.org/abs/2412.05631 · HTML: https://mlsanity.com/paper/2412.05631/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 7 Dec 2024.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [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)
- [Task Contamination: Language Models May Not Be Few-Shot Anymore](https://mlsanity.com/paper/2312.16337/) (2023)
- [MetaAgents: Large Language Model Based Agents for Decision-Making on Teaming](https://mlsanity.com/paper/2310.06500/) (2023)
- [Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works](https://mlsanity.com/paper/2404.12726/) (2024)
- [Urban Generative Intelligence (UGI): A Foundational Platform for Agents in Embodied City Environment](https://mlsanity.com/paper/2312.11813/) (2023)
- [TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models](https://mlsanity.com/paper/2405.18027/) (2024)

## Built on by (most cited first, 30 of 38)

- [Self-Supervised Prompt Optimization](https://mlsanity.com/paper/2502.06855/) (2025)
- [The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs](https://mlsanity.com/paper/2509.03730/) (2025)
- [How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation](https://mlsanity.com/paper/2502.14642/) (2025)
- [OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction](https://mlsanity.com/paper/2505.20277/) (2025)
- [Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions](https://mlsanity.com/paper/2512.12775/) (2025)
- [CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization](https://mlsanity.com/paper/2508.09074/) (2025)
- [The Dialogue That Heals: A Comprehensive Evaluation of Doctor Agents' Inquiry Capability](https://mlsanity.com/paper/2509.24958/) (2025)
- [Towards Interactive Intelligence for Digital Humans](https://mlsanity.com/paper/2512.13674/) (2025)
- [Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces](https://mlsanity.com/paper/2604.08362/) (2026)
- [Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs](https://mlsanity.com/paper/2603.19313/) (2026)
- [MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models?](https://mlsanity.com/paper/2506.13065/) (2025)
- [Dynamic Context Adaptation for Consistent Role-Playing Agents with Retrieval-Augmented Generations](https://mlsanity.com/paper/2508.02016/) (2025)
- [PTCBENCH: Benchmarking Contextual Stability of Personality Traits in LLM Systems](https://mlsanity.com/paper/2602.00016/) (2026)
- [Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs](https://mlsanity.com/paper/2605.00814/) (2026)
- [Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects](https://mlsanity.com/paper/2603.03915/) (2026)
- [Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models](https://mlsanity.com/paper/2604.10733/) (2026)
- [PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models](https://mlsanity.com/paper/2605.17044/) (2026)
- [RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing Agents](https://mlsanity.com/paper/2606.01552/) (2026)
- [GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph Learning](https://mlsanity.com/paper/2507.03267/) (2025)
- [Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axes](https://mlsanity.com/paper/2601.04716/) (2026)
- [Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents](https://mlsanity.com/paper/2603.01438/) (2026)
- [Beyond Static Personas: Situational Personality Steering for Large Language Models](https://mlsanity.com/paper/2604.13846/) (2026)
- [MemGround: Long-Term Memory Evaluation Kit for Large Language Models in Gamified Scenarios](https://mlsanity.com/paper/2604.14158/) (2026)
- [ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?](https://mlsanity.com/paper/2606.05553/) (2026)
- [Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives](https://mlsanity.com/paper/2608.08160/) (2026)
- [Hateful Person or Hateful Model? Investigating the Role of Personas in Hate Speech Detection by Large Language Models](https://mlsanity.com/paper/2506.08593/) (2025)
- [Understanding Generalization in Role-Playing Models via Information Theory](https://mlsanity.com/paper/2512.17270/) (2025)
- [Codified Finite-state Machines for Role-playing](https://mlsanity.com/paper/2602.05905/) (2026)
- [Spoiler Alert: Narrative Forecasting as a Metric for Tension in LLM Storytelling](https://mlsanity.com/paper/2604.09854/) (2026)
- [TRACE Bench: Task-driven Roleplay Agentic Checklist Evaluation](https://mlsanity.com/paper/2608.11236/) (2026)

## Abstract (arXiv)

Role-playing is a crucial capability of Large Language Models (LLMs), enabling a wide range of practical applications, including intelligent non-player characters, digital twins, and emotional companions. Evaluating this capability in LLMs is challenging due to the complex dynamics involved in role-playing, such as maintaining character fidelity throughout a storyline and navigating open-ended narratives without a definitive ground truth. Current evaluation methods, which primarily focus on question-answering or conversational snapshots, fall short of adequately capturing the nuanced character traits and behaviors essential for authentic role-playing. In this paper, we propose CharacterBox, which is a simulation sandbox designed to generate situational fine-grained character behavior trajectories. These behavior trajectories enable a more comprehensive and in-depth evaluation of role-playing capabilities. CharacterBox consists of two main components: the character agent and the narrator agent. The character agent, grounded in psychological and behavioral science, exhibits human-like behaviors, while the narrator agent coordinates interactions between character agents and environmental changes. Additionally, we introduce two trajectory-based methods that leverage CharacterBox to enhance LLM performance. To reduce costs and facilitate the adoption of CharacterBox by public communities, we fine-tune two smaller models, CharacterNR and CharacterRM, as substitutes for GPT API calls, and demonstrate their competitive performance compared to advanced GPT APIs.