From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench

• URL: http://arxiv.org/abs/2604.15037v2
• Date: Sat, 18 Apr 2026 03:00:05 GMT
• Title: From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench
• Abstract summary: We introduce ProVoice-Bench, the first evaluation framework specifically designed for proactive voice agents.<n>By leveraging a multi-stage data synthesis pipeline, we curate 1,182 high-quality samples for rigorous testing.<n>Our evaluation of state-of-the-art Multimodal LLMs reveals a significant performance gap, particularly regarding over-triggering and reasoning capabilities.
• Score: 11.985605415045734
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in LLM agents are gradually shifting from reactive, text-based paradigms toward proactive, multimodal interaction. However, existing benchmarks primarily focus on reactive responses, overlooking the complexities of proactive intervention and monitoring. To bridge this gap, we introduce ProVoice-Bench, the first evaluation framework specifically designed for proactive voice agents, featuring four novel tasks. By leveraging a multi-stage data synthesis pipeline, we curate 1,182 high-quality samples for rigorous testing. Our evaluation of state-of-the-art Multimodal LLMs reveals a significant performance gap, particularly regarding over-triggering and reasoning capabilities. These findings highlight the limitations of current models and offer a roadmap for developing more natural, context-aware proactive agents.

Related papers

• MP-Bench: Evaluating Voice Agents as a Multiparty Conversation Participant [138.90198190949545]
  We introduce MP-Bench, the first benchmark specifically designed to evaluate conversational speech systems as active participants within multi-party contexts.<n>MP-Bench assesses agent behavior along two primary dimensions: turn-taking awareness and response appropriateness.<n>We find that real-time voice agents stay at or below 22% on multiparty comprehension and remain near chance on multiparty turn-taking.
  arXiv  Detail & Related papers  (2026-09-11T17:11:55Z)
• IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams [13.326802573561748]
  multimodal large language models (MLLMs) achieve strong performance on reactive question answering, but real-world streaming assistants require proactive reasoning over continuous visual inputs.<n>We introduce IPIBench, the first benchmark for evaluating Interactive Intelligence of MLLMs under streaming video settings.<n>We propose IPI-Agent, a training-free agentic framework with an interaction-control policy and a temporal-gating mechanism for stabilizing proactive triggering and coordinating multi-turn interactions.
  arXiv  Detail & Related papers  (2026-05-26T14:23:25Z)
• ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models [51.06179253173491]
  We introduce ProactiveBench, a benchmark that tests proactiveness across different tasks.<n>We evaluate 22 MLLMs on ProactiveBench, showing that (i) they generally lack proactiveness; (ii) proactiveness does not correlate with model capacity; (iii) "hinting" at proactiveness yields only marginal gains.
  arXiv  Detail & Related papers  (2026-03-19T20:58:03Z)
• ProAct: A Benchmark and Multimodal Framework for Structure-Aware Proactive Response [20.913342340957904]
  ProAct-75 is a benchmark designed to train and evaluate proactive agents across diverse domains.<n>Our dataset features 91,581 step-level annotations enriched with explicit task graphs.<n>We propose ProAct-Helper, a reference baseline powered by a Multimodal Large Language Model (MLLM)
  arXiv  Detail & Related papers  (2026-02-03T11:52:19Z)
• AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding [73.05946667683259]
  Recent large language models (MLLMs) show strong perception but struggle in multi-speaker, dialogue-centric settings.<n>We introduce AMUSE, a benchmark designed around tasks that are inherently agentic.<n>We propose RAFT, a data-efficient agentic alignment framework that integrates reward optimization with intrinsic multimodal self-evaluation.
  arXiv  Detail & Related papers  (2025-12-18T07:01:47Z)
• ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents [29.03683444493195]
  We propose ProactiveEval, a unified framework for evaluating proactive dialogue capabilities of large language models (LLMs)<n>This framework decomposes proactive dialogue into target planning and dialogue guidance, establishing evaluation metrics across various domains.<n>We show that DeepSeek-R1 and Claude-3.7-Sonnet exhibit exceptional performance on target planning and dialogue guidance tasks.
  arXiv  Detail & Related papers  (2025-08-28T16:26:44Z)
• ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models [41.35497807436858]
  We introduce ProactiveVideoQA, the first comprehensive benchmark to evaluate a system's ability to engage in proactive interaction.<n>We also propose PAUC, the first metric that accounts for the temporal dynamics of model responses.<n>These findings demonstrate that PAUC provides a more faithful assessment of user experience in proactive interaction scenarios.
  arXiv  Detail & Related papers  (2025-07-12T15:11:50Z)
• On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows [71.92083784393418]
  Agentic AI (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low.<n>Inference-time alignment relies on three components: sampling, evaluation, and feedback.<n>We introduce Iterative Agent Decoding (IAD), a procedure that repeatedly inserts feedback extracted from different forms of critiques.
  arXiv  Detail & Related papers  (2025-04-02T17:40:47Z)
• Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities [93.09944267871163]
  FullDuplexBench is a benchmark that systematically evaluates key interactive behaviors.<n>By releasing our benchmark code we aim to advance spoken dialogue modeling and the development of more natural and engaging SDMs.
  arXiv  Detail & Related papers  (2025-03-06T18:59:16Z)
• Active Speakers in Context [88.22935329360618]
  Current methods for active speak er detection focus on modeling short-term audiovisual information from a single speaker. This paper introduces the Active Speaker Context, a novel representation that models relationships between multiple speakers over long time horizons. Our experiments show that a structured feature ensemble already benefits the active speaker detection performance.
  arXiv  Detail & Related papers  (2020-05-20T01:14:23Z)

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.