跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-06AI 評分36

HiPLEX: Hierarchical Policy Factorization for Full Duplex Speech Language Models

HiPLEX: Hierarchical Policy Factorization for Full Duplex Speech Language Models

AI 導讀

HiPLEX 提出一種強化學習框架,將預訓練的全雙工文字策略分解為控制策略與條件式內容策略,分別決定何時輸出內容及輸出甚麼。Full-Duplex-Bench v1 上的 Moshi 三個隨機種子測試顯示,HiPLEX 相較 GRPO 降低自然停頓及回應機會中的搶話率,並縮短受打斷後的回應延遲,同時維持相若的評審中斷回應品質。

正文

Published on Oct 6

Authors:

,

,

,

,

,

,

Abstract

As human--AI interactions become more conversational, full-duplex speech language models capable of natural real-time dialogue are growing in importance. Beyond generating appropriate responses, these models must coordinate turn-taking, backchanneling, and floor management in real time. Reinforcement learning (RL) provides a way to refine these behaviors through direct feedback on interaction outcomes. However, existing RL methods either apply timing feedback to a token policy or optimize semantic content, leaving the joint improvement of timing and content unresolved. We introduce HiPLEX, an RL framework that factorizes a pretrained full-duplex text policy into a control policy that decides when to emit content and a conditional content policy that decides what to emit. The first factor selects among 'pad', 'epad', and 'con'. The second selects a token only when 'con' is chosen. This hierarchy describes conditional actions within each frame and uses the model's existing text head. We route timing advantages to the token-group factor through event-causal masks derived from generated speech episodes, and route an LLM-judge semantic advantage to the conditional content factor. Across three Moshi seeds on Full-Duplex-Bench v1, HiPLEX reduces takeover rates during natural user pauses and backchannel opportunities, and shortens post-interruption response latency relative to GRPO, while maintaining comparable judged interruption-response quality. On Moshi and PersonaPlex, HiPLEX better matches pooled human turn-timing and backchannel-rate marginals than GRPO.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2610.07727

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.07727 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.07727 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.07727 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co