Great Listeners, Poor Decision-Makers: Rethinking Agentic Audio AI

Audio artificial intelligence (AI) now recognizes speech, sounds, and music remarkably well, yet voice agents still act when they should not: they execute commands addressed to others, act on misheard content, and commit before the user finishes speaking. This position article argues that the bottleneck in agentic audio AI has shifted from recognition to decision-making. We propose a reference architecture with an explicit decision layer, separate from perception and reasoning, that chooses whether to act, wait, ask, or remain silent from evidence on addressedness, speaker identity, content confidence, tool reliability, utterance completeness, and action risk. We motivate the design through six recurring decision failures and a decision-theoretic argument that transcript confidence alone is insufficient to justify an action. We implement the layer with fuzzy inference, evolutionary optimization, and sequential decision-making, and evaluate it through simulations, ablations, and recorded audio, including egocentric recordings. Addressedness and speaker evidence matter most, risk-aware gating suppresses costly errors, and well-tuned policies perform similarly, with fuzzy gates more robust to overconfident addressedness estimates. On recorded audio, explicit gating cuts executed side talk from 41\% to 7--10\% while serving 83--85\% of valid requests under successful clarification, outperforming prompting-based baselines. These results support explicit action gating as an architectural requirement for reliable voice agents.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-18
DOI
https://doi.org/10.48550/arxiv.2611.23847
Primary Topic
Speech and dialogue systems
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Great Listeners, Poor Decision-Makers: Rethinking Agentic Audio AI

Siddique Latif, Farrukh Pervez, Raja Jurdak, Moid Sandu
arXiv (Cornell University)
Speech and dialogue systems
preprint

Great Listeners, Poor Decision-Makers: Rethinking Agentic Audio AI

Siddique Latif, Farrukh Pervez, Raja Jurdak, Moid Sandu
preprint en

Abstract

Audio artificial intelligence (AI) now recognizes speech, sounds, and music remarkably well, yet voice agents still act when they should not: they execute commands addressed to others, act on misheard content, and commit before the user finishes speaking. This position article argues that the bottleneck in agentic audio AI has shifted from recognition to decision-making. We propose a reference architecture with an explicit decision layer, separate from perception and reasoning, that chooses whether to act, wait, ask, or remain silent from evidence on addressedness, speaker identity, content confidence, tool reliability, utterance completeness, and action risk. We motivate the design through six recurring decision failures and a decision-theoretic argument that transcript confidence alone is insufficient to justify an action. We implement the layer with fuzzy inference, evolutionary optimization, and sequential decision-making, and evaluate it through simulations, ablations, and recorded audio, including egocentric recordings. Addressedness and speaker evidence matter most, risk-aware gating suppresses costly errors, and well-tuned policies perform similarly, with fuzzy gates more robust to overconfident addressedness estimates. On recorded audio, explicit gating cuts executed side talk from 41\% to 7--10\% while serving 83--85\% of valid requests under successful clarification, outperforming prompting-based baselines. These results support explicit action gating as an architectural requirement for reliable voice agents.

arXiv (Cornell University)
Speech and dialogue systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon