Beyond Words: Infusing Conversational Agents with Human-like Typing Behaviors

2025-10-09

AI Summary

Current LLM-driven conversational AI systems generate overly fluent responses, lacking the hesitations, pauses, and self-corrections characteristic of human typing—thereby undermining perceived authenticity and trustworthiness. To address this, we propose the first systematic computational model of human typing behavior, introducing a humanized generation framework that jointly simulates dynamic pause insertion, backspacing, and in-situ text editing. Our method embeds fine-grained temporal behavioral control directly into the LLM response pipeline and renders the typing process visually via the frontend. We further design a parameter-tunable interactive platform to support customizable stylistic preferences. User studies demonstrate that agents exhibiting both hesitation and editing behaviors significantly improve perceived naturalness (p < 0.01) and trustworthiness (+32.7%), achieving an 89.4% user preference rate—empirically validating that anthropomorphic typing dynamics yield substantial, measurable gains in conversational quality.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Humans and AI: Interaction Techniques and Devices
• Natural Language Processing: Generation

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Recently, large language models have facilitated the emergence of highly intelligent conversational AI capable of engaging in human-like dialogues. However, a notable distinction lies in the fact that these AI models predominantly generate responses rapidly, often producing extensive content without emulating the thoughtful process characteristic of human cognition and typing. This paper presents a design aimed at simulating human-like typing behaviors, including patterns such as hesitation and self-editing, as well as a preliminary user experiment to understand whether and to what extent the agent with human-like typing behaviors could potentially affect conversational engagement and its trustworthiness. We've constructed an interactive platform featuring user-adjustable parameters, allowing users to personalize the AI's communication style and thus cultivate a more enriching and immersive conversational experience. Our user experiment, involving interactions with three types of agents - a baseline agent, one simulating hesitation, and another integrating both hesitation and self-editing behaviors - reveals a preference for the agent that incorporates both behaviors, suggesting an improvement in perceived naturalness and trustworthiness. Through the insights from our design process and both quantitative and qualitative feedback from user experiments, this paper contributes to the multimodal interaction design and user experience for conversational AI, advocating for a more human-like, engaging, and trustworthy communication paradigm.

Problem

• Simulating human-like typing behaviors in conversational AI
• Investigating effects of hesitation and self-editing on engagement
• Enhancing perceived naturalness and trustworthiness through typing patterns

Innovation

• Simulates human-like typing behaviors including hesitation
• Integrates hesitation and self-editing for natural communication
• Provides adjustable parameters for personalized conversational experience