Bridging the Perception Gap: A Lightweight Coarse-to-Fine Architecture for Edge Audio Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Hengfan, Lin, Yueqian, Li, Hai Helen, Chen, Yiran
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915746911617024
author Zhang, Hengfan
Lin, Yueqian
Li, Hai Helen
Chen, Yiran
author_facet Zhang, Hengfan
Lin, Yueqian
Li, Hai Helen
Chen, Yiran
contents Deploying Audio-Language Models (Audio-LLMs) on edge infrastructure exposes a persistent tension between perception depth and computational efficiency. Lightweight local models tend to produce passive perception - generic summaries that miss the subtle evidence required for multi-step audio reasoning - while indiscriminate cloud offloading incurs unacceptable latency, bandwidth cost, and privacy risk. We propose CoFi-Agent (Tool-Augmented Coarse-to-Fine Agent), a hybrid architecture targeting edge servers and gateways. It performs fast local perception and triggers conditional forensic refinement only when uncertainty is detected. CoFi-Agent runs an initial single-pass on a local 7B Audio-LLM, then a cloud controller gates difficult cases and issues lightweight plans for on-device tools such as temporal re-listening and local ASR. On the MMAR benchmark, CoFi-Agent improves accuracy from 27.20% to 53.60%, while achieving a better accuracy-efficiency trade-off than an always-on investigation pipeline. Overall, CoFi-Agent bridges the perception gap via tool-enabled, conditional edge-cloud collaboration under practical system constraints.
format Preprint
id arxiv_https___arxiv_org_abs_2601_15676
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Bridging the Perception Gap: A Lightweight Coarse-to-Fine Architecture for Edge Audio Systems
Zhang, Hengfan
Lin, Yueqian
Li, Hai Helen
Chen, Yiran
Sound
Machine Learning
Audio and Speech Processing
Deploying Audio-Language Models (Audio-LLMs) on edge infrastructure exposes a persistent tension between perception depth and computational efficiency. Lightweight local models tend to produce passive perception - generic summaries that miss the subtle evidence required for multi-step audio reasoning - while indiscriminate cloud offloading incurs unacceptable latency, bandwidth cost, and privacy risk. We propose CoFi-Agent (Tool-Augmented Coarse-to-Fine Agent), a hybrid architecture targeting edge servers and gateways. It performs fast local perception and triggers conditional forensic refinement only when uncertainty is detected. CoFi-Agent runs an initial single-pass on a local 7B Audio-LLM, then a cloud controller gates difficult cases and issues lightweight plans for on-device tools such as temporal re-listening and local ASR. On the MMAR benchmark, CoFi-Agent improves accuracy from 27.20% to 53.60%, while achieving a better accuracy-efficiency trade-off than an always-on investigation pipeline. Overall, CoFi-Agent bridges the perception gap via tool-enabled, conditional edge-cloud collaboration under practical system constraints.
title Bridging the Perception Gap: A Lightweight Coarse-to-Fine Architecture for Edge Audio Systems
topic Sound
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2601.15676