arXiv cs.AI· Arne Hildenbrand, Philipp Diel, Zhuo Cao, Hanno Scharr, Stefan Pischinger, Steffen Marburg·· 14 小时前AI 评分31
智能体系统在声学任务中的实际评估：模型与 harness 如何影响性能
Practical Assessment of Agentic Systems in Acoustics
AI 导读
一项研究在两类声学应用中实测了 LLM 智能体的表现：车内录音故障检测达到近乎完美的准确率，超材料单元胞设计能稳定找到满足指定频段插入损耗的方案。该任务的 benchmark 显示，弱模型构成 harness 设计无法突破的上限，设计选择只有在模型足够强时才生效。
正文 · 原文
Abstract:In engineering, applications of artificial intelligence have so far been largely limited to surrogate models and optimization tasks. Large language models changed this, as they can write software from a task given in words. Placed inside a harness, a system of components that lets it search for information and execute software, such a model becomes an agent that can take over recurring engineering tasks. This work measures how the model and the elements of the harness shape the performance and behavior of the agent in two common acoustic applications. In the first, the agent detects and locates faults in audio recordings from a vehicle interior with near-perfect accuracy. A benchmark on this task shows that a weak model sets a limit that no harness design can overcome, and that design choices take effect only once the model is capable enough to use them. In the second, a case study on the design of a metamaterial unit cell, the agent reliably finds designs that achieve a specified insertion loss over a given frequency range. The results aim to help the reader understand what each element of an agent contributes and how to design an agent for acoustic tasks.
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.39685 [cs.SD] |
| (or arXiv:2610.39685v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2610.39685 arXiv-issued DOI via DataCite |
Submission history
From: Arne Erik Hildenbrand [view email]
[v1]
Thu, 29 Oct 2026 09:29:07 UTC (2,591 KB)
来源：arXiv cs.AI · arxiv.org