SOURCE-LINKED INTELLIGENCE

DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

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 instructions, while deployed agents are often configured through roles or personas from which the appropriate conversational behavior must be inferred. We introduce DuplexSpeechBench-IFEval (DSB-IFEval) for evaluating implicit instruction-following in real-time spoken interaction. (DSB-IFEval) comprises 1,038 test cases spanning eight diverse assistant roles and evaluates fi

Read original source ↗ Open in workspace

recordType

paper

region

Global