ProAct: A Dual-System Framework for Proactive Embodied Social Agents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918339642654720 |
|---|---|
| author | Zhang, Zeyi Kang, Zixi Zhao, Ruijie Feng, Yusen Jiang, Biao Liu, Libin |
| author_facet | Zhang, Zeyi Kang, Zixi Zhao, Ruijie Feng, Yusen Jiang, Biao Liu, Libin |
| contents | Embodied social agents have recently advanced in generating synchronized speech and gestures. However, most interactive systems remain fundamentally reactive, responding only to current sensory inputs within a short temporal window. Proactive social behavior, in contrast, requires deliberation over accumulated context and intent inference, which conflicts with the strict latency budget of real-time interaction. We present \emph{ProAct}, a dual-system framework that reconciles this time-scale conflict by decoupling a low-latency \emph{Behavioral System} for streaming multimodal interaction from a slower \emph{Cognitive System} which performs long-horizon social reasoning and produces high-level proactive intentions. To translate deliberative intentions into continuous non-verbal behaviors without disrupting fluency, we introduce a streaming flow-matching model conditioned on intentions via ControlNet. This mechanism supports asynchronous intention injection, enabling seamless transitions between reactive and proactive gestures within a single motion stream. We deploy ProAct on a physical humanoid robot and evaluate both motion quality and interactive effectiveness. In real-world interaction user studies, participants and observers consistently prefer ProAct over reactive variants in perceived proactivity, social presence, and overall engagement, demonstrating the benefits of dual-system proactive control for embodied social interaction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_14048 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ProAct: A Dual-System Framework for Proactive Embodied Social Agents Zhang, Zeyi Kang, Zixi Zhao, Ruijie Feng, Yusen Jiang, Biao Liu, Libin Robotics Computer Vision and Pattern Recognition Graphics Embodied social agents have recently advanced in generating synchronized speech and gestures. However, most interactive systems remain fundamentally reactive, responding only to current sensory inputs within a short temporal window. Proactive social behavior, in contrast, requires deliberation over accumulated context and intent inference, which conflicts with the strict latency budget of real-time interaction. We present \emph{ProAct}, a dual-system framework that reconciles this time-scale conflict by decoupling a low-latency \emph{Behavioral System} for streaming multimodal interaction from a slower \emph{Cognitive System} which performs long-horizon social reasoning and produces high-level proactive intentions. To translate deliberative intentions into continuous non-verbal behaviors without disrupting fluency, we introduce a streaming flow-matching model conditioned on intentions via ControlNet. This mechanism supports asynchronous intention injection, enabling seamless transitions between reactive and proactive gestures within a single motion stream. We deploy ProAct on a physical humanoid robot and evaluate both motion quality and interactive effectiveness. In real-world interaction user studies, participants and observers consistently prefer ProAct over reactive variants in perceived proactivity, social presence, and overall engagement, demonstrating the benefits of dual-system proactive control for embodied social interaction. |
| title | ProAct: A Dual-System Framework for Proactive Embodied Social Agents |
| topic | Robotics Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2602.14048 |