mlsanityData to 14 Oct 2026

Full-Duplex-Bench-v2: A Multi-Turn Evaluation Framework for Duplex Dialogue Systems with an Automated Examiner

arXiv 2510.07838 ↗First posted 9 Oct 2025eess.AScited by 41

Not on the map. Why?

Abstract (arXiv)

While full-duplex speech agents enable natural, low-latency interaction by speaking and listening simultaneously, their consistency and task performance in multi-turn settings remain underexplored. We introduce Full-Duplex-Bench-v2 (FDB-v2), a streaming framework that integrates with an automated examiner that enforces staged goals under two pacing setups (Fast vs. Slow). FDB-v2 covers four task families: daily, correction, entity tracking, and safety. We report turn-taking fluency, multi-turn instruction following, and task-specific competence. The framework is extensible, supporting both commercial APIs and open source models. When we test full-duplex systems with FDB-v2, they often get confused when people talk at the same time, struggle to handle corrections smoothly, and sometimes lose track of who or what is being talked about. Through an open-sourced, standardized streaming protocol and a task set, FDB-v2 makes it easy to extend to new task families, allowing the community to tailor and accelerate evaluation of multi-turn full-duplex systems.

Key facts. Cited by 41 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Oct 2025.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 40.

41 papers.

Sort:

By area:

  1. 2026Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluencycited by 37
  2. 2026τ-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domainscited by 36
  3. 2025MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Modelscited by 22
  4. 2026Multi-Faceted Interactivity Alignment in Full-Duplex Speech Modelscited by 10
  5. 2026Raon-Speech Technical Reportcited by 7
  6. 2026TurnBench: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialoguecited by 7
  7. 2026Instruct-FD: Can Your Full-Duplex Speech System Follow Turn-Taking Instructions?cited by 6
  8. 2026Optimizing Conversational Quality in Spoken Dialogue Systems with Reinforcement Learning from AI Feedbackcited by 5
  9. 2026EchoChain: A Full-Duplex Benchmark for State-Update Reasoning Under Interruptionscited by 5
  10. 2026IHBench: Evaluating Post-Interruption Recovery in Voice Agents with Structured Workflowscited by 5
  11. 2026OmniInteract: Benchmarking Real-World Streaming Interaction for Real-Time Omnimodal Assistantscited by 4
  12. 2026Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steeringcited by 4
29 more
  1. 2026DuplexWorld: Can voice agents help you get through the day?cited by 4
  2. 2026MSI-Bench: Evaluating Multi-Speaker Voice Interaction for Collaborative AI Agentscited by 4
  3. 2026ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Modelscited by 3
  4. 2026M3-DuplexBench: A Multi-Turn, Multilingual, Multidomain Benchmark for Full-Duplex Spoken Dialogue Modelscited by 3
  5. 2026MTVA-Bench: Evaluating the Language Model Inside Cascaded Voice Agentscited by 3
  6. 2026MP-Bench: Evaluating Voice Agents as a Multiparty Conversation Participantcited by 2
  7. 2026Same Words, Different Actions: Paired Turn-Taking Evaluation under Rewritten Dialogue Contextscited by 2
  8. 2026A frontend-backend architecture for tool calls in full-duplex speech modelscited by 2
  9. 2026TiCo: Time-Controllable Spoken Dialogue Modelcited by 1
  10. 2026VideoFDB: Evaluating Full-Duplex Vision-Speech Capabilities in Conversational Agentscited by 1
  11. 2026A Reliability Assessment of LALM Audio Judges for Full-Duplex Voice Agentscited by 1
  12. 2026DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agentscited by 1
  13. 2026Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal Interactioncited by 1
  14. 2026MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversationcited by 1
  15. 2026PACE: A Playback-Aligned Context Engine for LLM-Based Full-Duplex Voice Dialoguecited by 0
  16. 2026Enabling Proactive Spoken Turns via a Generalized Style-Aware Full-Duplex Frameworkcited by 0
  17. 2026When Patients Cut In: Extending Clinical Conversational AI Safety to Interruptionscited by 0
  18. 2026DuplexJail: Safety Alignment Breaks Under Spoken Interruption in Full-Duplex Modelscited by 0
  19. 2026SteerDuplex: Steerable Duplex Speech Dialogue Modelscited by 0
  20. 2026Continue, Adapt, or Yield: In-Turn Adaptation to Overlapping Speech in Full-Duplex Agentscited by 0
  21. 2026Neither Silence nor Overlap Is Failure: Intent-Conditioned Evaluation of Turn-Taking in Full-Duplex Spoken Dialogue Modelscited by 0
  22. 2026Evaluating Real-Time Voice Agents: From Component Quality to Grounded Outcomescited by 0
  23. 2026Distributional Metrics for Evaluating Spoken Conversational Systemscited by 0
  24. 2026When Does a Spoken Agent Have Enough Evidence to Act? The PACT-SLM Contract Testcited by 0
  25. 2026DuplexAct-Bench: Broadening Full-Duplex Speech Evaluation toward Proactive Interaction across Diverse Behavioral Requirementscited by 0
  26. 2026DuplexSpeechBench-Document Grounding: Benchmarking Document Grounding and Hallucinations in Voice Agentscited by 0
  27. 2026People Making Conversation: Evaluating How Naturally Speech Models Conversecited by 0
  28. 2026DuplexAct: How Interactive Are Frontier Full-Duplex Spoken Language Models?cited by 0
  29. 2026MultiPartyTurnBench: Benchmarking Floor Control in Multi-Party Spoken Dialoguecited by 0