English(EN) DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents

新基准评估语音代理中的隐式指令遵循

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-04 04:00

引入了一个新的基准 DuplexSpeechBench-IFEval (DSB-IFEval)，用于评估全双工语音代理根据角色或个性隐式遵循指令的能力，而不是显式命令。该基准包含八个助手角色下的 1,038 个测试用例，并衡量指令遵循度和个性一致性。初步测试显示，虽然 F-Actor 和 PersonaPlex 等模型对指令类型敏感，但 GPT-Realtime 和 MiniCPM-o 等模型在个性一致性方面表现出色，但在适应不同指令方法的楼层行为方面存在困难。 AI

影响该基准可以通过提高语音代理从上下文中推断用户意图的能力，从而实现更自然、更直观的语音代理交互。

排序理由该集群包含一篇介绍用于评估 AI 系统的新基准的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 17 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇介绍用于评估 AI 系统的新基准的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Puneet Mathur, Dinesh Manocha · 2026-09-04 04:00

DuplexSpeechBench-IFEval：评估全双工语音代理中的隐式指令遵循

arXiv:2609.03423v1 Announce Type: new Abstract: Full-duplex voice agents must continuously decide when to listen, backchannel, interrupt, handle speech overlaps, take the floor, and yield. Existing benchmarks largely test these behaviors through explicit turn-management instructi…

本文如何被排名

报道来源 [1]

DuplexSpeechBench-IFEval：评估全双工语音代理中的隐式指令遵循

相关实体

相关话题