# Adaptive Test-Time Scaling for Zero-Shot Respiratory Audio Classification

arXiv: https://arxiv.org/abs/2604.12647 · HTML: https://mlsanity.com/paper/2604.12647/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)

## Builds on (most cited first, 15 of 15)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Deep Learning Scaling is Predictable, Empirically](https://mlsanity.com/paper/1712.00409/) (2017)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [AudioCLIP: Extending CLIP to Image, Text and Audio](https://mlsanity.com/paper/2106.13043/) (2021)
- [Archon: An Architecture Search Framework for Inference-Time Techniques](https://mlsanity.com/paper/2409.15254/) (2024)
- [Jina CLIP: Your CLIP Model Is Also Your Text Retriever](https://mlsanity.com/paper/2405.20204/) (2024)
- [Provable Scaling Laws for the Test-Time Compute of Large Language Models](https://mlsanity.com/paper/2411.19477/) (2024)
- [RespLLM: Unifying Audio and Text with Multimodal LLMs for Generalized Respiratory Health Prediction](https://mlsanity.com/paper/2410.05361/) (2024)
- [CaReAQA: A Cardiac and Respiratory Audio Question Answering Model for Open-Ended Diagnostic Reasoning](https://mlsanity.com/paper/2505.01199/) (2025)
- [CLAP: Learning Audio Concepts From Natural Language Supervision](https://mlsanity.com/paper/2206.04769/) (2022)
- [Language Models as Semantic Teachers: Post-Training Alignment for Medical Audio Understanding](https://mlsanity.com/paper/2512.04847/) (2025)

## Abstract (arXiv)

Automated respiratory audio analysis promises scalable, non-invasive disease screening, yet progress is limited by scarce labeled data and costly expert annotation. Zero-shot inference eliminates task-specific supervision, but existing methods apply uniform computation to every input regardless of difficulty. We introduce TRIAGE, a tiered zero-shot framework that adaptively scales test-time compute by routing each audio sample through progressively richer reasoning stages: fast label-cosine scoring in a joint audio-text embedding space (Tier-L), structured matching with clinician-style descriptors (Tier-M), and retrieval-augmented large language model reasoning (Tier-H). A confidence-based router finalizes easy predictions early while allocating additional computation to ambiguous inputs, enabling nearly half of all samples to exit at the cheapest tier. Across nine respiratory classification tasks without task-specific training, TRIAGE achieves a mean AUROC of 0.744, outperforming prior zero-shot methods and matching or exceeding supervised baselines on multiple tasks. Our analysis show that test-time scaling concentrates gains where they matter: uncertain cases see up to 19% relative improvement while confident predictions remain unchanged at minimal cost.