← 研踪 PaperTrailarXiv:2611.23847 · v1
Great Listeners, Poor Decision-Makers: Rethinking Agentic Audio AI
首次提交 2026-11-18 12:52
版本更新 2026-11-18 12:52
雷达观测 2026-11-19 19:08
摘要
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.
作者备注:Under-review, work in progress
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-18 12:52 · 最新观测版本
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.
查看此版本解读 →查看此版本原文 ↗