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

arXiv: https://arxiv.org/abs/2602.11065 · HTML: https://mlsanity.com/paper/2602.11065/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 18 of its 59 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)

## Builds on (most cited first, 18 of 18)

- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities](https://mlsanity.com/paper/2503.04721/) (2025)
- [Dialogue State Tracking with a Language Model using Schema-Driven Prompting](https://mlsanity.com/paper/2109.07506/) (2021)
- [Voice Activity Projection: Self-supervised Learning of Turn-taking Events](https://mlsanity.com/paper/2205.09812/) (2022)
- [Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2305.16582/) (2023)
- [Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics](https://mlsanity.com/paper/2503.01174/) (2025)
- [Dialogue Act Classification with Context-Aware Self-Attention](https://mlsanity.com/paper/1904.02594/) (2019)
- [MIDAS: A Dialog Act Annotation Scheme for Open Domain Human Machine Spoken Conversations](https://mlsanity.com/paper/1908.10023/) (2019)
- [Speaker Turn Modeling for Dialogue Act Classification](https://mlsanity.com/paper/2109.05056/) (2021)
- [Learning in the Rational Speech Acts Model](https://mlsanity.com/paper/1510.06807/) (2015)
- [Turn-Taking Prediction for Natural Conversational Speech](https://mlsanity.com/paper/2208.13321/) (2022)
- [EmotionThinker: Prosody-Aware Reinforcement Learning for Explainable Speech Emotion Reasoning](https://mlsanity.com/paper/2601.15668/) (2026)
- [When can I Speak? Predicting initiation points for spoken dialogue agents](https://mlsanity.com/paper/2208.03812/) (2022)
- [A Streaming End-to-End Framework For Spoken Language Understanding](https://mlsanity.com/paper/2105.10042/) (2021)
- [Sequential End-to-End Intent and Slot Label Classification and Localization](https://mlsanity.com/paper/2106.04660/) (2021)
- [Prior Lessons of Incremental Dialogue and Robot Action Management for the Age of Language Models](https://mlsanity.com/paper/2501.00953/) (2025)
- [Beyond Classification: Towards Speech Emotion Reasoning with Multitask AudioLLMs](https://mlsanity.com/paper/2506.06820/) (2025)

## Abstract (arXiv)

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.