提出自适应多角色互动框架，提升虚拟角色扮演的沉浸感与动态适应能力。
AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing
- 设计沉浸式消息格式与场景管理器，支持动态角色引入和场景切换。
- 在8B模型上超越多个商用大模型，14B模型表现超过Claude Sonnet 4.5。
- 适用于需要复杂角色交互与场景演进的互动叙事系统开发。
LLM角色扮演旨在在交互叙事中塑造任意角色，但现有系统常因沉浸感不足与适应性差而受限。它们普遍忽视环境动态信息，假设场景和角色基本静态，难以支持多角色协同、场景转换及实时角色引入。本文提出自适应多智能体角色扮演框架AdaMARP，采用融合[思考]、(行动)、<环境>与对话的沉浸式消息格式，并引入显式场景管理器，通过离散动作（init_scene、pick_speaker、switch_scene、add_role、end）及理由来控制角色扮演过程。为训练该能力，构建了用于演员建模的AdaRPSet和用于调度决策的AdaSMSet，提出AdaptiveBench进行轨迹级评估。多骨干模型与不同规模实验表明：AdaRPSet显著提升角色一致性、环境锚定与叙事连贯性，8B模型性能优于多个商用LLM；AdaSMSet实现更流畅的场景转换与自然的角色引入，仅用14B模型即超越Claude Sonnet 4.5。
原文摘要 · Abstract (English)
LLM role-playing aims to portray arbitrary characters in interactive narratives, yet existing systems often suffer from limited immersion and adaptability. They typically under-model dynamic environmental information and assume largely static scenes and casts, offering insufficient support for multi-character orchestration, scene transitions, and on-the-fly character introduction. We propose an adaptive multi-agent role-playing framework, AdaMARP, featuring an immersive message format that interleaves [Thought], (Action), <Environment>, and Speech, together with an explicit Scene Manager that governs role-playing through discrete actions (init_scene, pick_speaker, switch_scene, add_role, end) accompanied by rationales. To train these capabilities, we construct AdaRPSet for the Actor Model and AdaSMSet for supervising orchestration decisions, and introduce AdaptiveBench for trajectory-level evaluation. Experiments across multiple backbones and model scales demonstrate consistent improvements: AdaRPSet enhances character consistency, environment grounding, and narrative coherence, with an 8B actor outperforming several commercial LLMs, while AdaSMSet enables smoother scene transitions and more natural role introductions, surpassing Claude Sonnet 4.5 using only a 14B LLM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。