# RAIDEN-R1: Improving Role-awareness of LLMs via GRPO with Verifiable Reward

arXiv: https://arxiv.org/abs/2505.10218 · HTML: https://mlsanity.com/paper/2505.10218/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 11 of its 22 references that are in the map.
- First posted on arXiv 15 May 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 11 of 11)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [Iteratively Prompt Pre-trained Language Models for Chain of Thought](https://mlsanity.com/paper/2203.08383/) (2022)
- [CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models](https://mlsanity.com/paper/2311.16832/) (2023)
- [Reasoning Does Not Necessarily Improve Role-Playing Ability](https://mlsanity.com/paper/2502.16940/) (2025)
- [BEYOND DIALOGUE: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model](https://mlsanity.com/paper/2408.10903/) (2024)
- [CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis](https://mlsanity.com/paper/2501.01668/) (2025)

## Built on by (most cited first, 13 of 13)

- [REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2505.24760/) (2025)
- [Too Good to be Bad: On the Failure of LLMs to Role-Play Villains](https://mlsanity.com/paper/2511.04962/) (2025)
- [HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing](https://mlsanity.com/paper/2601.21459/) (2026)
- [MOA: Multi-Objective Alignment for Role-Playing Agents](https://mlsanity.com/paper/2512.09756/) (2025)
- [Character-R1: Enhancing Role-Aware Reasoning in Role-Playing Agents via RLVR](https://mlsanity.com/paper/2601.04611/) (2026)
- [RoleRMBench & RoleRM: Towards Reward Modeling for Profile-Based Role Play in Dialogue Systems](https://mlsanity.com/paper/2512.10575/) (2025)
- [LLMs vs. Chinese Anime Enthusiasts: A Comparative Study on Emotionally Supportive Role-Playing](https://mlsanity.com/paper/2508.06388/) (2025)
- [Understanding Generalization in Role-Playing Models via Information Theory](https://mlsanity.com/paper/2512.17270/) (2025)
- [TRACE Bench: Task-driven Roleplay Agentic Checklist Evaluation](https://mlsanity.com/paper/2608.11236/) (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)
- [Adversarial Closed-Loop Curriculum for Evolving Role-Playing Agents](https://mlsanity.com/paper/2609.28609/) (2026)
- [TRACER: Trajectory-Aligned Learning for Multi-Turn User Simulation](https://mlsanity.com/paper/2609.28690/) (2026)

## Abstract (arXiv)

Role-playing conversational agents (RPCAs) face persistent challenges in maintaining role consistency. To address this, we propose RAIDEN-R1, a novel reinforcement learning framework that integrates Verifiable Role-Awareness Reward (VRAR). The method introduces both singular and multi-term mining strategies to generate quantifiable rewards by assessing role-specific keys. Additionally, we construct a high-quality, role-aware Chain-of-Thought dataset through multi-LLM collaboration, and implement experiments to enhance reasoning coherence. Experiments on the RAIDEN benchmark demonstrate RAIDEN-R1's superiority: our 14B-GRPO model achieves 88.04% and 88.65% accuracy on Script-Based Knowledge and Conversation Memory metrics, respectively, outperforming baseline models while maintaining robustness. Case analyses further reveal the model's enhanced ability to resolve conflicting contextual cues and sustain first-person narrative consistency. This work bridges the non-quantifiability gap in RPCA training and provides insights into role-aware reasoning patterns, advancing the development of RPCAs.