Reasoning in Full-Duplex Speech with Graph-of-Thoughts
Research Paper#Conversational AI, Speech Processing, Causal Inference, Graph Neural Networks🔬 Research|Analyzed: Jan 4, 2026 00:15•
Published: Dec 25, 2025 15:00
•1 min read
•ArXivAnalysis
This paper addresses the challenge of building more natural and intelligent full-duplex interactive systems by focusing on conversational behavior reasoning. The core contribution is a novel framework using Graph-of-Thoughts (GoT) for causal inference over speech acts, enabling the system to understand and predict the flow of conversation. The use of a hybrid training corpus combining simulations and real-world data is also significant. The paper's importance lies in its potential to improve the naturalness and responsiveness of conversational AI, particularly in full-duplex scenarios where simultaneous speech is common.
Key Takeaways
- •Introduces a Graph-of-Thoughts (GoT) framework for causal reasoning in full-duplex speech.
- •Employs a hierarchical labeling scheme to model intent-to-action pathways.
- •Utilizes a hybrid training corpus combining simulated and real-world data.
- •Enables robust behavior detection and interpretable reasoning chains.
- •Establishes a foundation for benchmarking conversational reasoning in full duplex spoken dialogue systems.
Reference / Citation
View Original"The GoT framework structures streaming predictions as an evolving graph, enabling a multimodal transformer to forecast the next speech act, generate concise justifications for its decisions, and dynamically refine its reasoning."