SCB: SpeechConversationBench (SCB) evaluates multi-turn reasoning in speech-to-speech models by using 103 sharded GSM8K mathematical problems. The benchmark compares three delivery modes: a full single-turn problem, a concatenated multi-shard version, and an incremental spoken disclosure across turns. Results show that sharded accuracy drops by 5.0–25.3 percentage points for four commercial systems, while the internal LEGO pipeline maintains 77.5% accuracy across all conditions, outperforming GPT‑4o Realtime’s 76.6% sharded accuracy.
arXiv:2609.13076v1 Announce Type: cross Abstract: Conversational voice agents have advanced significantly, offering increasingly natural human-machine interactions through both cascaded and end-to-en...
arXiv:2609.38867v1 Announce Type: new Abstract: Large language model (LLM) computer-use agents are typically evaluated with clean written instructions, despite speech being an increasingly popular in...
Scalable Context Orchestration for Serving LLMs Over Voice presents llmovoice, a middleware that explicitly models voice context—including speaking rate, background noise, and packet loss—to guide large language model responses. By constructing a bounded voice context at each turn, llmovoice improves alignment with user preferences and reduces errors, achieving a 52.4% drop in speaking‑rate alignment error and a 0.9% false‑interruption rate under packet loss. In addition, it cuts model usage costs dramatically, lowering per‑turn cost by up to 24.9× while maintaining 98.7% of baseline answer quality in long sessions.
arXiv:2603.16783v2 Announce Type: replace Abstract: Robust voice agents require exposure to the full diversity of how people interact through speech. However, obtaining enough spoken interactions is...
arXiv:2609.22214v1 Announce Type: new Abstract: Long multilingual conversational spoken question answering requires systems to balance long-range transcript semantics with sparse acoustic and speaker...
The paper introduces llmovoice, a middleware that explicitly models voice context for large language model (LLM) serving in voice AI applications. By incorporating speaking rate, background noise, packet loss, and other paralinguistic factors into a bounded context, llmovoice guides the LLM to generate more aligned responses. Experiments show significant reductions in speaking‑rate errors, false interruptions, and model usage costs, especially in long voice sessions.
arXiv:2609.09852v1 Announce Type: new Abstract: The advance of multimodal large language models (MLLMs) has fundamentally reshaped the paradigm of human-computer interaction, especially speech intera...
The paper introduces a frontend‑backend architecture for full‑duplex speech‑to‑speech models that enables tool calls while preserving natural conversational flow. The frontend emits a delegation token and streams ASR transcripts to a text‑based backend LLM, which performs tool calls and returns results that are re‑injected into the frontend via a lightweight prefill‑and‑repeat mechanism before streaming TTS synthesis. In single‑turn evaluations the system achieves 92‑97% tool‑call recall, 81.2% accuracy in rejecting irrelevant calls, and competitive performance on Full‑Duplex‑Bench‑V3 and EVA‑Bench when paired with a large backend model.
arXiv:2608.27783v3 Announce Type: replace-cross Abstract: Speech language models (speech LLMs) can generate plausible outputs from audio that contains no usable speech evidence. We study this failure...
arXiv:2609.24812v1 Announce Type: new Abstract: Voice provides a natural and immediate interface for AI agents. Many settings in which voice agents could be useful, including meetings, households, an...
arXiv:2607. 21180v1 Announce Type: new Abstract: Recent advances have introduced speech-to-speech (S2S) conversational assistants capable of producing natural-sounding interactions, including non-verbal cues like tonality and mood.
arXiv:2606. 13544v1 Announce Type: cross Abstract: Turn-taking in multi-party spoken conversations remains a fundamental challenge for voice-based agents, particularly under dynamic floor competition and varying user expectations.