Pith. sign in

REVIEW 6 cited by

Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2409.15594 v1 pith:4BCWFKVU submitted 2024-09-23 cs.CL cs.LGcs.SDeess.AS

classification cs.CLcs.LGcs.SDeess.AS
keywords dialoguefull-duplexllmsspokenagentsdatamodelingsynchronous
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Despite broad interest in modeling spoken dialogue agents, most approaches are inherently "half-duplex" -- restricted to turn-based interaction with responses requiring explicit prompting by the user or implicit tracking of interruption or silence events. Human dialogue, by contrast, is "full-duplex" allowing for rich synchronicity in the form of quick and dynamic turn-taking, overlapping speech, and backchanneling. Technically, the challenge of achieving full-duplex dialogue with LLMs lies in modeling synchrony as pre-trained LLMs do not have a sense of "time". To bridge this gap, we propose Synchronous LLMs for full-duplex spoken dialogue modeling. We design a novel mechanism to integrate time information into Llama3-8b so that they run synchronously with the real-world clock. We also introduce a training recipe that uses 212k hours of synthetic spoken dialogue data generated from text dialogue data to create a model that generates meaningful and natural spoken dialogue, with just 2k hours of real-world spoken dialogue data. Synchronous LLMs outperform state-of-the-art in dialogue meaningfulness while maintaining naturalness. Finally, we demonstrate the model's ability to participate in full-duplex dialogue by simulating interaction between two agents trained on different datasets, while considering Internet-scale latencies of up to 240 ms. Webpage: https://syncllm.cs.washington.edu/.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Evaluating AI Models' Capability to Automate Voice Phishing Attacks

    cs.CR 2026-07 conditional novelty 7.0 of 10

    AI voice models already drive self-reported vishing compliance up to 36% and make automated attacks economically viable at U.S. scale while human operators are not.

  2. The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning

    eess.AS 2026-03 unverdicted novelty 7.0 of 10

    FLAIR enables spoken dialogue AI to conduct continuous latent reasoning while perceiving speech through recursive latent embeddings and an ELBO-based finetuning objective.

  3. Scalable phonon-laser arrays with self-organized synchronization

    quant-ph 2026-03 unverdicted novelty 6.0 of 10

    Local driving of an Ising-like spin–mechanical chain yields scalable, site-addressable phonon lasers with resonance conditions, on-demand lasing, and self-organized synchronization.

  4. NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction

    cs.CL 2025-06 conditional novelty 6.0 of 10

    NTPP models dual-channel spoken dialogue by predicting both speakers' next speech tokens as a pair, achieving speaker-independent full-duplex generation in a decoder-only transformer.

  5. SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A speech-to-speech language model uses channel fusion of a streaming encoder and codec tokens to handle barge-in and turn-taking without speech pretraining, showing improved metrics over Moshi at 0.6 kbps.

  6. Chain-of-Thought Training for Open E2E Spoken Dialogue Systems

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Staged ASR-to-text-response-to-TTS training makes open end-to-end spoken dialogue systems trainable on 300 hours of public human-human data and more coherent than one-step speech-to-speech models.

Pith tools