Don't Wait to Reply: Towards Responsive yet Thoughtful Dialogue through Proactive Thinking
2026-07-03 • Computation and Language
Computation and LanguageArtificial Intelligence
AI summaryⓘ
The authors explore how language models usually wait to start reasoning until a user says something, which causes delays in conversations. They propose 'Proactive Thinking,' where the model uses quiet moments to prepare possible answers ahead of time, making chats smoother and faster. They test this idea using special benchmarks that mimic real-time talks and find that it helps without hurting quality. Their work suggests chat AIs can be smarter by thinking in advance, like humans do in conversations.
Large Language ModelsConversational AIProactive ThinkingSpeculative Continual ThinkingReal-time InteractionLatencyBenchmarksNatural Language ProcessingDialogue Systems
Authors
Ante Wang, Jiaqi Fu, Xuanyi Chen, Ruotian Ma, Zhaopeng Tu, Weizhi Ma, Yang Liu
Abstract
Thinking has emerged as a critical capability for Large Language Models (LLMs) tackling complex tasks. However, its reactive nature, where reasoning is passively triggered only upon receiving a user response, inevitably introduces latency that compromises conversational fluidity. This stands in sharp contrast to human dialogue, where speakers proactively anticipate and plan future content during natural pauses to ensure seamless interaction. To bridge this gap, we propose Proactive Thinking, a framework that empowers models to pre-compute potential response elements during conversational downtime instead of waiting idly for the next input. We then introduce a training-free baseline that can think ahead by anticipating future states, balancing efficiency and quality through speculative continual thinking. To evaluate this approach in practice, we adapt three benchmarks of varying complexity into time-aware environments that simulate real-time conversational flow. We demonstrate that proactive thinking effectively improves interaction efficiency without compromising performance. Ultimately, this work advocates for a fundamental shift toward more intelligent, anticipatory, and real-time conversational AI.