DuplexSpeechBench-IFEval (DSB-IFEval) is a new benchmark that evaluates how full‑duplex voice agents follow implicit instructions during real‑time spoken interaction. It contains 1,038 test cases across eight assistant roles and tests five conditioning protocols, measuring floor management with an Instruction Adherence Score (IAS) and persona consistency with a Persona Adherence Score (PAS). Experiments on six speech systems reveal architecture‑dependent trade‑offs, showing that some models are more sensitive to explicit versus persona‑only instructions and that even when following conflicting directives, they struggle to override them under safety conflict.
arXiv:2607. 20460v1 Announce Type: cross Abstract: Current full-duplex (FD) spoken dialogue systems can produce fluid interactions, yet it remains unclear whether they can adapt their turn-taking behavior when explicitly instructed.
arXiv:2609.13117v1 Announce Type: new Abstract: Full-duplex evaluation often emphasizes whether an agent keeps speaking or stops. That binary cannot express a third response humans use routinely: con...
SteerDuplex is a full‑duplex speech dialogue model that can be steered along attributes such as tone, persona, speaking rate, and voice style in response to user instructions. The authors introduce a taxonomy of text‑ and audio‑based steerability, identify gaps in existing models, and fine‑tune a Moshi‑based model with reinforcement learning to improve timing and response continuity. They also present SteerBench, a benchmark of 390 spoken prompts and 1,067 human‑authored rubrics, showing significant gains in audio‑steering pass rates and interruption handling compared to open baselines.
arXiv:2609.13814v1 Announce Type: new Abstract: Natural interaction in digital and physical environments requires continuous perception and timely responses. Spoken dialogue relies on acoustic and li...
ECHO is a new paired diagnostic benchmark designed for Chinese full‑duplex spoken dialogue systems to evaluate context‑sensitive turn‑taking. It pairs examples that share the same overlap transcript but differ in preceding multi‑turn context, requiring either a Yield or Keep decision, and also includes off‑talk cases to test unnecessary yielding. The benchmark introduces pair accuracy, penalizing constant‑action policies, and shows that many systems are biased toward Yield, performing better on interruptions than on backchannels.
arXiv:2608.28630v1 Announce Type: cross Abstract: Compared with half-duplex dialogue systems where the system waits for user turn completion before it responds, natural full-duplex dialogue systems r...
Prosodic cues can convey task-relevant information that alters the trajectory and outcome of a task-oriented dialogue, even when the words themselves remain unchanged. Yet existing benchmarks typically evaluate prosodic perception, response appropriateness, and task-oriented dialogue in isolation, making it difficult to test whether prosodic evidence changes downstream decisions.
arXiv:2608. 19515v1 Announce Type: new Abstract: Prosodic cues can convey task-relevant information that alters the trajectory and outcome of a task-oriented dialogue, even when the words themselves remain unchanged.
The paper evaluates the use of large language models (LLMs) as judges for assessing conversational voice agents, comparing human judgments with GPT‑4.1 and GPT‑5 across telecom and retail interactions. It examines agreement, metric‑level correlations, and consistency across three evaluation configurations (p0, p1, p2) to determine how reliably LLMs can judge conversational quality and safety. The study finds that LLM‑based evaluation can be effective but its reliability varies by metric and configuration, suggesting a hybrid approach where LLMs handle scalable assessment while humans focus on metrics requiring contextual interpretation.
arXiv:2606. 19595v1 Announce Type: cross Abstract: Voice agents deployed in structured workflows (customer service, healthcare scheduling, account management) must handle frequent user interruptions while maintaining progress through multi-step procedures.
CallScreenBench is a benchmark for evaluating small, on-device language models that act as phone secretaries, focusing on their ability to handle unknown inbound calls without a cooperative task. The benchmark measures owner endorsement through five call-and-note metrics, each paired with counter-metrics and uncertainty estimates, and includes guardedness diagnostics to identify safe, tool‑free proxies. Results across 4‑bit checkpoints of 0.6‑4 B parameter models show varying performance on service, recall, plausibility, and triage discrimination, highlighting trade‑offs between quality and guardedness.
arXiv:2606. 07547v1 Announce Type: cross Abstract: Speech-based large language models are typically constrained to spoken replies, which limits their user-facing outputs to what can be verbalized and suppresses text-native capabilities such as code generation, structured analysis, and multi-step reasoning in realtime interaction, for tasks that require persistent, structured, and inspectable intermediate outputs.