AnyAudio-Judge: A Dynamic Rubric-Based Benchmark and Evaluator for Audio Instruction Following

research work·benchmark study·active

Research work examining audio generation, evaluation benchmark.

Recorded facts

Official site	https://arxiv.org/abs/2606.03116 ↗
Geography	Global
arxiv	2606.03116
venue	arXiv preprint
authors	Haitao Li; Tian Tan; Yuguang Yang; Shan Yang; Xie Chen
methods	benchmark evaluation; language modeling; reinforcement learning
code urls	unknown
demo urls	unknown
exact title	AnyAudio-Judge: A Dynamic Rubric-Based Benchmark and Evaluator for Audio Instruction Following
project urls	unknown
original title	unknown
citation counts	unknown
research topics	audio generation; evaluation benchmark
peer review status	not established from abstract metadata
disclosed conflicts	unknown
stated contribution	Presents or evaluates the system, method, benchmark, or analysis identified in the paper title.
us market scope basis	Included as a materially relevant public research artifact in the US-facing AI-music ecosystem; direct affiliation varies.
funding acknowledgements	unknown
affiliations at publication	unknown
publication or preprint date	2026-06-02
abstract level neutral summary	The work studies audio generation, evaluation benchmark; methods and evaluation details are in the official abstract.
datasets benchmarks models tools used	unknown
correction withdrawal retraction status	No withdrawal marker observed in captured arXiv metadata.