ACL Findings2026
AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing
Zhenhua Xu, Dongsheng Chen, Shuo Wang, Jian Li, Chengjie Wang, Meng Han, Yabiao Wang
Abstract
LLM role-playing seeks to portray arbitrary characters in interactive narratives, yet existing systems often lack immersion and adaptability. They typically under-model dynamic environment information and assume a largely static scene/cast, offering limited support for multi-character orchestration, scene transitions, and on-the-fly character introduction. We propose an adaptive multi-agent interaction framework dubbed AdaMARP, which featuring an immersive message format that interleaves [Thought], (Action), <Environment>, and Speech, and an explicit Scene Manager that controls role-playing via discrete actions (init_scene, pick_speaker, switch_scene, add_role, end) with rationales. To train these abilities, we construct AdaRPSet for the Actor Model and AdaSMSet for supervising orchestration decisions, and introduce Adap-tiveBench for trajectory-level evaluation. Experiments across multiple backbones and scales show consistent gains: AdaRPSet improves character consistency, environment grounding, and narrative coherence-an 8B actor outperforming several commercial LLMs, while AdaSMSet enables smoother scene transitions and more natural role introductions, surpassing Claude Sonnet 4.5 with only 14B LLMs. Our code and datasets are publicly available at ht tps://xuzhenhua55.github.io/AdaMARP
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models cites Large Language Models Meet Harry Potter: A Dataset for Aligning Dialogue Agents with Characters
- TailorRPA: A Retrieval-Based Framework for Eliciting Personalized and Coherent Role-Playing Agents in General Domain cites Large Language Models Meet Harry Potter: A Dataset for Aligning Dialogue Agents with Characters
- TailorRPA: A Retrieval-Based Framework for Eliciting Personalized and Coherent Role-Playing Agents in General Domain cites TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models
- Crab: A Novel Configurable Role-Playing LLM with Assessing Benchmark cites Large Language Models Meet Harry Potter: A Dataset for Aligning Dialogue Agents with Characters
Cited by top-tier papers2
- When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent SystemsNaen Xu, Hengyu An, Shuo Shi, Jinghuai Zhang et al.ICLR 2026 · 3 citations
- "I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?Naen Xu, Jiayi Sheng, Changjiang Li, Chunyi Zhou et al.ACL 2026 · 1 citation
Builds on5
- Large Language Models Meet Harry Potter: A Dataset for Aligning Dialogue Agents with CharactersNuo Chen, Yan Wang, Haiyun Jiang, Deng Cai et al.EMNLP Findings 2023 · 28 citations
- "Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative UnderstandingFaeze Brahman, Meng Huang, Oyvind Tafjord, Chao Zhao et al.EMNLP Findings 2021 · 20 citations
- TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language ModelsJaewoo Ahn, Taehyun Lee, Junyoung Lim, Jin-Hwa Kim et al.ACL Findings 2024 · 9 citations
- TailorRPA: A Retrieval-Based Framework for Eliciting Personalized and Coherent Role-Playing Agents in General DomainZhenpeng Gao, Xiaofen Xing, Xiangmin XuEMNLP Findings 2025
- Crab: A Novel Configurable Role-Playing LLM with Assessing BenchmarkKai He, Yucheng Huang, Wenqing Wang, Delong Ran et al.ACL 2025
Related papers
- Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing AgentXiaoyan Yu, Tongxu Luo, Yifan Wei, Fangyu Lei et al.EMNLP 2024 · 4 citations
- HAMLET: A Hierarchical and Adaptive Multi-Agent Framework for Live Embodied TheatricsShufan Jiang, Sizhou Chen, Chi Zhang, Xiao-Lei Zhang et al.ICLR 2026 · 2 citations
- RolePlot: A Systematic Framework for Evaluating and Enhancing the Plot-Progression Capabilities of Role-Playing AgentsPinyi Zhang, Siyu An, Lingfeng Qiao, Yifei Yu et al.ACL 2025 · 4 citations
- DMT-RoleBench: A Dynamic Multi-Turn Dialogue Based Benchmark for Role-Playing Evaluation of Large Language Model and AgentDingbo Yuan, Yipeng Chen, Guodong Liu, Chenchen Li et al.AAAI 2025 · 6 citations
- Exploring Large Language Model-Driven Agents for Environment-Aware Spatial Interactions and Conversations in Virtual Reality Role-Play ScenariosZiming Li, Huadong Zhang, Chao Peng, Roshan L. PeirisIEEE VR 2025 · 18 citations
