Conversational Behavior Modeling Foundation Model With Multi-Level Perception

TL;DR

This paper introduces a multi-level perception framework with a Graph-of-Thoughts for modeling conversational behaviors, enabling interpretable reasoning and improved behavior detection in full-duplex dialogue systems.

Contribution

It proposes a novel hierarchical perception and reasoning framework with a new corpus, advancing conversational behavior modeling and interpretability.

Findings

Robust behavior detection in synthetic and real dialogues

Generation of interpretable reasoning chains

Foundation for benchmarking conversational reasoning

Abstract

Human conversation is organized by an implicit chain of thoughts that manifests as timed speech acts. Capturing this perceptual pathway is key to building natural full-duplex interactive systems. We introduce a framework that models this process as multi-level perception, and then reasons over conversational behaviors via a Graph-of-Thoughts (GoT). Our approach formalizes the intent-to-action pathway with a hierarchical labeling scheme, predicting high-level communicative intents and low-level speech acts to learn their causal and temporal dependencies. To train this system, we develop a high quality corpus that pairs controllable, event-rich dialogue data with human-annotated labels. The GoT framework structures streaming predictions as an evolving graph, enabling a transformer to forecast the next speech act, generate concise justifications for its decisions, and dynamically refine its reasoning. Experiments on both synthetic and real duplex dialogues show that the framework delivers robust behavior detection, produces interpretable reasoning chains, and establishes a foundation for benchmarking conversational reasoning in full duplex spoken dialogue systems.