Test-Time-Matching：在基于 LLM 的角色扮演语言智能体中解耦人格、记忆与语言风格
Test-Time-Matching: Decouple Personality, Memory, and Linguistic Style in LLM-based Role-Playing Language Agent
AI总结：
针对 LLM 角色扮演中提示沉浸不足与微调成本高的问题，本文提出免训练的 TTM 框架，自动解耦人格、记忆和语言风格，并通过三阶段流程生成高保真、风格一致的角色对话。
摘要：
大型语言模型（LLM）的快速发展，使角色扮演语言智能体在各类应用中展现出巨大潜力。然而，仅依赖提示词和上下文输入，往往不足以实现对特定角色的深度沉浸，尤其是著名虚构人物或公众人物。另一方面，基于微调的方法受限于数据收集难题以及训练所需的计算资源，从而限制了其更广泛的适用性。为解决这些问题，我们提出 Test-Time-Matching（TTM），这是一种通过测试时扩展和上下文工程实现的免训练角色扮演框架。TTM 使用 LLM 智能体自动将角色特征解耦为人格、记忆和语言风格。我们的框架包含一个结构化的三阶段生成流程，利用这些特征进行可控的角色扮演。它实现了高保真的角色扮演表现，还支持在不同语言风格之间、甚至在人格和记忆的变化之间进行无缝组合。我们通过人工评估对框架进行评测，结果表明，我们的方法在生成富有表现力且风格一致的角色对话方面取得了卓越性能。
英文摘要：
The rapid advancement of large language models (LLMs) has enabled role-playing language agents to demonstrate significant potential in various applications. However, relying solely on prompts and contextual inputs often proves insufficient for achieving deep immersion in specific roles, particularly well-known fictional or public figures. On the other hand, fine-tuning-based approaches face limitations due to the challenges associated with data collection and the computational resources required for training, thereby restricting their broader applicability. To address these issues, we propose Test-Time-Matching (TTM), a training-free role-playing framework through test-time scaling and context engineering. TTM uses LLM agents to automatically decouple a character's features into personality, memory, and linguistic style. Our framework involves a structured, three-stage generation pipeline that utilizes these features for controlled role-playing. It achieves high-fidelity role-playing performance, also enables seamless combinations across diverse linguistic styles and even variations in personality and memory. We evaluate our framework through human assessment, and the results demonstrate that our method achieves the outstanding performance in generating expressive and stylistically consistent character dialogues.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
