The paper evaluates how large language models, when integrated into a harness that provides information retrieval and software execution, perform as agents in acoustic engineering tasks. In one experiment, the agent accurately detects and locates faults in vehicle interior audio recordings, showing that a weak model limits performance regardless of harness design. In a second case study, the agent reliably designs metamaterial unit cells to meet specified insertion loss targets across a frequency range, illustrating the agent’s practical utility in acoustic design.
By Arne Hildenbrand, Philipp Diel, Zhuo Cao, Hanno Scharr, Stefan Pischinger, Steffen Marburg
A real-time auditory scene analyzer (ASA) aims to carry out the tasks of locating, separating and classifying the sound sources present in a given acoustic environment. Recently, an effort has been ma...
The paper presents a real‑time auditory scene analyzer (ASA) modeled as a multi‑agent system, where each agent handles locating, separating, or classifying sound sources and shares results to correct local errors globally. By replacing single‑window quality estimates with sets of estimations across a range of locations, the authors achieve faster, more accurate, and more stable optimization of speech‑source localization, even in real‑life acoustic scenarios. The new mechanism reduces optimization time and complexity, though it slightly increases the response time of the quality‑estimation agent, while the overall ASA remains real‑time capable.
By Caleb Rascon
arXiv:2606. 15141v1 Announce Type: cross Abstract: While LALMs show promise on audio question answering, they fail to focus on question-relevant segments of audio and provide a clear, checkable reasoning process when dealing with complex audio reasoning.
By Siyuan Zhang, Jian Zong, Junyu Wang, Peiyuan Jiang, Jiahao Yan, Jingyu Zhang, Tianrui Wang, Xiaobao Wang, Longbiao Wang, Jianwu Dang
arXiv:2610.27670v1 Announce Type: new
Abstract: This paper introduces a novel framework for efficiently evaluating in-game sound designs using multimodal learning and reinforcement learning. Sound de...
By Thai Nguyen Van, Ibrahim Khan, Mury Fajar Dewantoro, Pratch Suntichaikul, Hai Van Pham, Ruck Thawonmas
AbsorbEvo is an agentic framework that autonomously designs microwave absorbers by translating natural‑language performance goals into full‑wave‑simulated designs. It combines language reasoning, physics‑based prediction, and historical feedback to guide a candidate evolution strategy, using a low‑cost predictive model to rank designs before simulation. In tests on AbsorbBench‑36, AbsorbEvo achieved a 79.17% task success rate, outperforming generic agents and random search.
By Zhicheng Feng, Yubo Zhao, Xuefeng Yao
SpeechGym is an audio‑native environment that lets two omni‑modal models converse entirely in native audio, eliminating external ASR/TTS and API boundaries while preserving the tasks, tools, and success checks of a standard text‑based agent benchmark. By training end‑to‑end, the framework addresses perceptual failures—such as misheard arguments that cascade into failed calls—and behavioural failures, both of which are automatically labeled for free. Using per‑turn process rewards to overcome reward sparsity, agents trained in SpeechGym transfer to an independent voice benchmark, doubling task success and improving efficiency in turns and tokens.
By Jiajun Fan, Jingyuan Li, Prashanth Gurunath Shivakumar, Jia-Hong Huang, Qi Luo, M. Maruf, Ivan Bulyko, Ge Liu, Roger Ren
The paper introduces KVoiceBench, KOpenAudioBench, and KMMAU—three Korean speech benchmarks created through agent-driven frameworks that adapt existing SpokenQA and ASR resources into Korean SpokenQA and audio understanding tasks. These benchmarks total 12,345 samples and are publicly released to evaluate SpeechLMs beyond English. The authors benchmark eight recent SpeechLMs, revealing significant English‑Korean performance gaps and divergent rankings between SpokenQA and audio understanding, highlighting multilingual weaknesses not apparent in English-only tests.
By Haechan Kim, Seungjun Chung, Inkyu Park, Jihoo Lee, Jonghyun Lee
Designing high-performance microwave absorbers requires specialized expertise in electromagnetic theory, materials science and simulation programming, and entails time-consuming optimization. Here, we...
AdaLoop is a lightweight recurrent module that adaptively determines how many latent refinement steps are needed for audio–question pairs, allowing deeper reasoning only when necessary. It shares a transformer block that iterates over the audio representation guided by the question, with a learned halting mechanism that exits the loop once the representation is ready. Adding fewer than 3 % of the base model’s parameters, AdaLoop improves average accuracy by 2.9 to 3.8 points across three distinct models, especially on perception-heavy subtasks.
By Lee Seung-woo, Bowen Qi
The paper introduces SEAR, a four-task benchmark that evaluates audio language models (ALMs) for audio deepfake detection by requiring acoustic evidence identification, quantification, deepfake detection, and forensic rationale generation. It also proposes BAEA, an acoustic evidence agent that equips a frozen ALM with controlled acoustic tools under fixed or adaptive evidence-acquisition policies. Experiments with six ALMs show a gap between plausible rationales and verifiable acoustic evidence reasoning, and demonstrate that BAEA‑Fixed improves final verdicts and forensic rationales while revealing that misleading evidence harms detection and grounding performance.
By Rong Wan, Suliu Qin, Jiaxi Li, Wei Xie, Wenwu Wang, Xiaolong Han, Lu Yin, Xilu Wang
AgentSWE is a new benchmark for agent software engineering that evaluates coding agents across three lifecycle stages: creating an agent from a natural‑language requirement, editing existing agent codebases, and optimizing toward a measurable target. The benchmark consists of 25 commission‑style tasks, where builders iterate on a few illustrative cases and are then tested on held‑out cases that cover the full requirement, with hard pass/fail gates or objective‑based grading. Experiments show that current coding agents fail to meet the requirements, revealing common failure modes such as overfitting, incomplete runtimes, and unsupported completion claims.
By Jiahao Wang, Hongjin Qian, Yuyang Hu, Jiajun Zhang, Zheng Liu