paper
Adaptive Turn-Taking for Real-time Multi-Party Voice Agents
paperactiveprovisional
adaptive-turn-taking-for-real-time-multi-party-voice-agents-57072f6d·1 events·first seen 5d agoAliases: Adaptive Turn-Taking for Real-time Multi-Party Voice Agents
Co-occurring entities
More like this (12)
foreground-background dual-agent voice architectureContext-Driven Incremental Compression for Multi-Turn Dialogue GenerationContext-Driven Incremental Compression for Multi-Turn Dialogue GenerationMulti-Faceted Interactivity Alignment in Full-Duplex Speech Modelsmulti-turn agent benchmarksOpenAI WebRTC Audio SessionMulti-Turn Evaluation of Deep Research Agents Under Process-Level FeedbackMulti-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight Adaptation in Three-Sided Dispatchtool-augmented language agentsconversational agentsspeech-to-avatar systemsActive Listening
Recent events (1)
ModeratorLM: Role-conditioned turn-taking for multi-party voice agents with 40%+ precision gains
Researchers introduce ModeratorLM, a voice agent system that conditions turn-taking behavior on an explicitly assigned conversational role in multi-party settings, built on a streaming speech LLM. A reasoning-augmented variant adds chain-of-thought over conversational context. Evaluated on real-world meeting data and the new RolePlayConv synthetic dataset, the system achieves over 40% improvement in turn-taking precision and 70% in recall while reducing false-positive interruptions versus non-role-conditioned baselines.