发表机构
Shandong University; University of Science and Technology of China; Central Conservatory of Music; Kunlun Tech Co. Ltd.; Shanghai Jiao Tong University（山东大学; 中国科学技术大学; 中央音乐学院; 昆仑万维科技股份有限公司; 上海交通大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对文生音乐中用户意图对齐不足的问题，提出MIRA代理，通过清单化意图并搜索提示修订，提升生成音乐与用户意图的一致性，使开源模型达到商业系统水平。
AI 中文摘要
文生音乐系统能生成越来越逼真的音频，然而评估却很少能揭示结果是否符合用户意图。全局的文本-音频相关性分数可能会忽略不明确提示中的隐含意图，并掩盖特定要求（如乐器、结构、节奏或情绪变化）上的失败。为弥合这一差距，我们将文生音乐的意图对齐形式化为满足每个请求的独立可验证项清单，该清单涵盖请求的明确要求和隐含的音乐意图。逐项评分使评估可按意图来源和音乐维度进行诊断，而非单一的不透明分数。我们将其实现为MuRA-Bench，一个由音乐专家策划的真实平台请求基准。我们进一步提出MIRA（音乐意图细化代理），一种测试时代理，它首先将请求的意图落实到清单中，然后在有限预算下对黑盒生成器的提示修订进行搜索，迭代地生成音乐，对照清单进行验证，并利用反馈指导轨迹感知的树搜索。在开源和商业后端的实验表明，MIRA提高了意图对齐，使开源生成器能达到与代表性商业系统（如Suno和Mureka）相当的性能。项目页面：此https URL。
英文摘要
Text-to-music systems produce increasingly convincing audio, yet evaluation reveals little about whether the result matches user intent. A global text-audio relevance score can overlook the implicit intent in underspecified prompts and mask failures in specific requirements, such as instrumentation, structure, rhythm, or mood progression. To bridge this gap, we formulate text-to-music intent alignment as satisfying a per-request rubric of independently verifiable items covering both a request's explicit requirements and its implied musical intent. Scoring items individually makes evaluation diagnostic by intent source and musical dimension, rather than a single opaque score. We instantiate this as MuRA-Bench, a benchmark of real-world platform requests curated by music experts. We further propose MIRA (Musical Intent Refinement Agent), a test-time agent that first grounds a request's intent into rubrics, then searches over prompt revisions for a black-box generator under a bounded budget, iteratively generating music, verifying it against the rubrics, and using this feedback to guide a trajectory-aware tree search. Experiments across open-source and commercial backends show that MIRA improves intent alignment, enabling an open-source generator to achieve performance comparable to representative commercial systems (e.g. Suno and Mureka). Project page: https://mirareview.github.io/.
