Multimodal Duplex Interaction Agent

• URL: http://arxiv.org/abs/2609.08977v3
• Date: Sat, 12 Sep 2026 11:55:26 GMT
• Title: Multimodal Duplex Interaction Agent
• Abstract summary: Gander is an interaction model that processes streaming user inputs, enabling full interaction in both everyday conversations and complex scenarios.<n>We evaluate Gander across conversational ability, interactive capability, understanding, and tool assisted task execution.<n>Gander supports a range of challenging interaction settings, including background noise interference, multi-party interactions, and backchannel communication.
• Score: 48.78411737142625
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we present Gander, a native multimodal duplex interaction model that builds on MiniCPM-o 4.5 and is further adapted for realtime interaction with an asynchronous agent loop. In contrast to conventional turn based systems, Gander continuously processes streaming user inputs, enabling full-duplex interaction in both everyday conversations and complex workflow agent scenarios. Users can interrupt an ongoing response, while the model can proactively provide intermediate feedback or ask follow up questions. To natively support these capabilities, Gander adopts two key architectural designs: 1) a Cerebellum-Brain collaborative framework, Cerebellum is responsible for realtime interaction while the Brain handles complex reasoning and higher level agentic tasks. The two components interact continuously through tool calling and the agent orchestration runtime. 2) The Cerebellum is built upon a streaming Thinker-Talker architecture, where user inputs and model outputs are flattened into an ordered token stream at the chunk level. We evaluate Gander across conversational ability, interactive capability, understanding, and tool assisted task execution. Internal human evaluations show that Gander maintains natural and expressive spoken dialogue, while benchmark results demonstrate effective turn taking capability and encouraging results on spoken question answering and related understanding tasks. Gander also supports a range of challenging interaction settings, including background noise interference, multi-party interactions, and backchannel communication. While our current evaluation focuses on tool assisted settings, broader long horizon agent tasks and more diverse deployment conditions remain promising directions for further study. We release Gander together with its models, code, and data to facilitate further research and development in the community.

Related papers

• Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models [53.470209949659115]
  We propose a post-training alignment method that improves full spoken dialogue models through RL.<n>We address the four canonical axes of interactivity: handling turn-taking, back-channel pause, and user interruption.<n>An extra-based reward for response quality prevents semantic degradation.
  arXiv  Detail & Related papers  (2026-06-09T17:46:55Z)
• VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions [63.13827503828231]
  We introduce VitaBench 2.0, a benchmark for evaluating personalized and proactive agent behavior in long-term user interactions.<n>Results show that real-world personalization remains highly challenging even for state-of-the-art models.
  arXiv  Detail & Related papers  (2026-05-26T15:07:38Z)
• MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models [62.05118198431989]
  Asynchronous full-speech models are distinguished by their full-time interactivity and naturalness of AI pauses.<n>Our framework enables the model to identify knowledge-demand conversational queries and ground responses in external information.<n>Our design supports plug-and-play retrieval methods without retraining and demonstrates strong performance on out-of-toe reasoning tasks.
  arXiv  Detail & Related papers  (2026-04-14T16:17:52Z)
• InterDyad: Interactive Dyadic Speech-to-Video Generation by Querying Intermediate Visual Guidance [20.740979380270126]
  We propose InterDyad, a synthesis framework for interactive dyadic dynamics.<n>We first design an Interactivity that achieves video reenactment based on identity-agnostic motion priors extracted from reference videos.<n>By leveraging a Multimodal Large Language Model (MLLM), our framework is able to distill linguistic intent from audio to dictate the precise timing and appropriateness of reactions.<n> Comprehensive experiments demonstrate that InterDyad significantly outperforms state-of-the-art methods in producing natural and contextually grounded two-person interactions.
  arXiv  Detail & Related papers  (2026-03-24T12:27:52Z)
• Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning [66.52010873968383]
  We introduce a conversational agent that interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through reinforcement learning (RL) training.<n>The experimental results across four widely used conversational benchmarks demonstrate the effectiveness of our methods.
  arXiv  Detail & Related papers  (2026-01-19T14:55:54Z)
• Interact2Ar: Full-Body Human-Human Interaction Generation via Autoregressive Diffusion Models [80.28579390566298]
  We introduce Interact2Ar, a text-conditioned autoregressive diffusion model for generating full-body, human-human interactions.<n>Hand kinematics are incorporated through dedicated parallel branches, enabling high-fidelity full-body generation.<n>Our model enables a series of downstream applications, including temporal motion composition, real-time adaptation to disturbances, and extension beyond dyadic to multi-person scenarios.
  arXiv  Detail & Related papers  (2025-12-22T18:59:50Z)
• Diffusion Forcing for Multi-Agent Interaction Sequence Modeling [52.769202433667125]
  MAGNet is a unified autoregressive diffusion framework for multi-agent motion generation.<n>It supports a wide range of interaction tasks through flexible conditioning and sampling.<n>It captures both tightly synchronized activities and loosely structured social interactions.
  arXiv  Detail & Related papers  (2025-12-19T18:59:02Z)
• End-to-end Listen, Look, Speak and Act [22.047534228540783]
  ELLSA represents a step toward more natural and general interactive intelligence, contributing to the broader pursuit of artificial intelligence.<n>At its core is a novel SA-MoE (Attention Mixture-of-Experts) that routes each modality to specialized experts fuses them through a unified attention backbone.
  arXiv  Detail & Related papers  (2025-10-19T08:45:46Z)
• Seamless Interaction: Dyadic Audiovisual Motion Modeling and Large-Scale Dataset [113.25650486482762]
  We introduce the Seamless Interaction dataset, a large-scale collection of over 4,000 hours of face-to-face interaction footage.<n>This dataset enables the development of AI technologies that understand dyadic embodied dynamics.<n>We develop a suite of models that utilize the dataset to generate dyadic motion gestures and facial expressions aligned with human speech.
  arXiv  Detail & Related papers  (2025-06-27T18:09:49Z)
• Breaking Single-Tester Limits: Multi-Agent LLMs for Multi-User Feature Testing [15.383375235673954]
  We propose MAdroid, a novel multi-agent approach powered by the Large Language Models (LLMs) to automate the multi-user interactive task for app feature testing.<n>Specifically, MAdroid employs two functional types of multi-agents: user agents (Operator) and supervisor agents (Coordinator and Observer)<n>Our evaluation, which included 41 multi-user interactive tasks, demonstrates the effectiveness of our approach, achieving 82.9% of the tasks with 96.8% action similarity.
  arXiv  Detail & Related papers  (2025-06-21T01:38:53Z)
• Inter-Diffusion Generation Model of Speakers and Listeners for Effective Communication [4.49451692966442]
  This paper proposes an Inter-Diffusion Generation Model of Speakers and Listeners for Effective Communication.<n>For the first time, we integrate the full-body gestures of listeners into the generation framework.
  arXiv  Detail & Related papers  (2025-05-08T07:00:58Z)
• It Takes Two: Real-time Co-Speech Two-person's Interaction Generation via Reactive Auto-regressive Diffusion Model [34.94330722832987]
  We introduce an audio-driven, auto-regressive system designed to synthesize dynamic movements for two characters during a conversation.<n>To the best of our knowledge, this is the first system capable of generating interactive full-body motions for two characters from speech in an online manner.
  arXiv  Detail & Related papers  (2024-12-03T12:31:44Z)
• MUG: Interactive Multimodal Grounding on User Interfaces [12.035123646959669]
  We present MUG, a novel interactive task for multimodal grounding where a user and an agent work collaboratively on an interface screen. Prior works modeled multimodal UI grounding in one round: the user gives a command and the agent responds to the command. MUG allows multiple rounds of interactions such that upon seeing the agent responses, the user can give further commands for the agent to refine or even correct its actions.
  arXiv  Detail & Related papers  (2022-09-29T21:08:18Z)
• A Probabilistic Model Of Interaction Dynamics for Dyadic Face-to-Face Settings [1.9544213396776275]
  We develop a probabilistic model to capture the interaction dynamics between pairs of participants in a face-to-face setting. This interaction encoding is then used to influence the generation when predicting one agent's future dynamics. We show that our model successfully delineates between the modes, based on their interacting dynamics.
  arXiv  Detail & Related papers  (2022-07-10T23:31:27Z)
• Multi-Domain Dialogue Acts and Response Co-Generation [34.27525685962274]
  We propose a neural co-generation model that generates dialogue acts and responses concurrently. Our model achieves very favorable improvement over several state-of-the-art models in both automatic and human evaluations.
  arXiv  Detail & Related papers  (2020-04-26T12:21:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.