arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.11065cs.CLcs.AI

S-MARC：全双工对话行为建模的因果流式推理

S-MARC: Causal Streaming Reasoning for Full-Duplex Conversational Behavior Modeling

University of California, Berkeley（加州大学伯克利分校）；Zhejiang University（浙江大学）；South China University of Technology（华南理工大学）
Dingkun Zhou, Shuchang Pan, Jiachen Lian, Siddharth Banerjee, Sarika Pasumarthy, Dhruv Hebbar, Siddhant Patel, Zeyi Austin Li, Kan Jen Cheng, Sanay Bordia, Kris… 展开作者

Dingkun Zhou, Shuchang Pan, Jiachen Lian, Siddharth Banerjee, Sarika Pasumarthy, Dhruv Hebbar, Siddhant Patel, Zeyi Austin Li, Kan Jen Cheng, Sanay Bordia, Krish Patel, Akshaj Gupta, Tingle Li, Gopala Anumanchipalli

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出S-MARC框架，通过流式因果层次建模意图到动作路径，预测高层交际功能和低层交互行为，并构建高质量语料库，实现全双工对话中的鲁棒行为检测与可解释推理。

摘要：

人类对话由隐式的思维链组织，并表现为时间结构化的对话行为。捕捉这一感知路径对于构建自然的全双工交互系统至关重要。我们提出了S-MARC（对话的流式因果建模与推理），一个用于对话行为建模与推理的流式、因果、层次化框架。通过形式化意图到动作的路径，S-MARC预测高层交际功能和低层交互行为，同时建模它们的因果和时间依赖关系。为支持这一设置，我们构建了一个高质量语料库，将可控、事件丰富的双工对话数据与行为标签配对。S-MARC将流式预测组织成持续演化的图结构，为其决策生成简洁的推理依据，并动态优化其推理过程。在合成和真实双工对话上的实验表明，S-MARC实现了鲁棒的行为检测，产生了可解释的推理链，并为全双工口语对话系统中的对话推理建立了基准基础。

英文摘要：

Human conversation is organized by an implicit chain of thought and manifests as temporally structured conversational behaviors. Capturing this perceptual pathway is critical for building natural full-duplex interactive systems. We propose S-MARC (Streaming Causal Modeling and Reasoning for Conversation), a streaming, causal, and hierarchical framework for conversational behavior modeling and reasoning. By formalizing the intent-to-action pathway, S-MARC predicts high-level communicative functions and low-level interaction behaviors while modeling their causal and temporal dependencies. To support this setting, we construct a high-quality corpus that pairs controllable, event-rich duplex dialogue data with behavior labels. S-MARC organizes streaming predictions into a continuously evolving graph structure, generates concise justifications for its decisions, and dynamically optimizes its reasoning process. Experiments on synthetic and real duplex dialogues show that S-MARC achieves robust behavior detection, produces interpretable reasoning chains, and establishes a benchmark foundation for conversational reasoning in full-duplex spoken dialogue systems.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑