# ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?

arXiv: https://arxiv.org/abs/2606.05553 · HTML: https://mlsanity.com/paper/2606.05553/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 41 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 22 of 22)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [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)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation](https://mlsanity.com/paper/2401.01275/) (2024)
- [Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics](https://mlsanity.com/paper/2406.14703/) (2024)
- [The Oscars of AI Theater: A Survey on Role-Playing with Language Models](https://mlsanity.com/paper/2407.11484/) (2024)
- [CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds](https://mlsanity.com/paper/2412.05631/) (2024)
- [The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs](https://mlsanity.com/paper/2509.03730/) (2025)
- [LiveChat: A Large-Scale Personalized Dialogue Dataset Automatically Constructed from Live Streaming](https://mlsanity.com/paper/2306.08401/) (2023)
- [How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation](https://mlsanity.com/paper/2502.14642/) (2025)
- [COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas](https://mlsanity.com/paper/2205.00872/) (2022)
- [Mitigating Hallucination in Fictional Character Role-Play](https://mlsanity.com/paper/2406.17260/) (2024)
- [Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions](https://mlsanity.com/paper/2512.12775/) (2025)
- [CharacterGPT: A Persona Reconstruction Framework for Role-Playing Agents](https://mlsanity.com/paper/2405.19778/) (2024)
- [HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing](https://mlsanity.com/paper/2601.21459/) (2026)
- [Towards Enhanced Immersion and Agency for LLM-based Interactive Drama](https://mlsanity.com/paper/2502.17878/) (2025)
- [Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation](https://mlsanity.com/paper/2506.19352/) (2025)
- [Quantifying Data Contamination in Psychometric Evaluations of LLMs](https://mlsanity.com/paper/2510.07175/) (2025)

## Built on by (most cited first, 2 of 2)

- [Emergi-PersonaOS: A Persona Agent Operating System for Situational Adaptation and Controllable Evolution](https://mlsanity.com/paper/2609.27417/) (2026)
- [Scaling Long-Form Story Generation via Narrative State Tracking](https://mlsanity.com/paper/2609.35759/) (2026)

## Abstract (arXiv)

Role-playing language agents (RPLAs) simulate specific characters and personas across applications such as entertainment, companionship, interactive storytelling, and education. Faithful role-play requires more than producing plausible, in-character responses: as a character's values and behavior change over a narrative, an RPLA should reflect the character's state at the relevant stage. However, existing benchmarks largely treat characters as fixed personas or test only what they know at a given point in the narrative. We introduce ArcANE (Arc-Aware Narrative Evaluation), a benchmark for evaluating whether an RPLA follows a character's development across a narrative. ArcANE first builds an Arc that maps how a character's values, motivations, or relationships change over the story. The benchmark then scores how well an RPLA's responses fit the corresponding stages of the Arc, covering three distinct scenario types: scenes from the novel, new situations within its world, and situations outside that world. We evaluate six models under six ways of providing narrative context. In every model, using the Arc up to the queried chapter yields the best performance, outperforming the strongest non-Arc context by 2.2-8.4 points. These results suggest that faithful role-play requires evolving character states and tracking their trajectory, rather than merely retrieving relevant episodic evidence.