GraphiMind：面向信息图形设计的以 LLM 为中心的界面
GraphiMind: LLM-centric Interface for Information Graphics Design
AI总结：
本文提出以 LLM 为中心的智能体界面 GraphiMind，结合文本对话与图形操作，依据自然语言意图自动生成、推荐并组合信息图形资源，降低非专业用户的设计门槛。
摘要：
信息图形在有效信息传播和叙事中至关重要。然而，对非专业人士而言，创作此类图形极具挑战性，因为设计过程需要多方面技能和全面知识。因此，尽管已有许多可用的创作工具，但在帮助非专家顺畅地创作引人注目的信息图形方面仍存在显著差距，尤其是从零开始创作。近期突破表明，大型语言模型（LLM），特别是在工具增强的情况下，能够自主调用外部工具，因而成为实现创新图形设计应用的有力候选。在本研究中，我们提出一种以 LLM 为中心的界面，并通过智能体 GraphiMind，根据用户以自然语言表达的意图，自动生成、推荐和组合信息图形设计资源。我们的 GraphiMind 将由工具增强型 LLM 驱动的文本对话界面与传统的图形操作界面相结合，简化了从原始资源整理到组合与细化的整个设计流程。大量评估突显了该工具在简化设计过程方面的熟练能力，为非专业用户使用它开辟了途径。此外，我们还强调了 LLM 在重塑信息图形设计领域方面的潜力，其融合了自动化、多功能性和以用户为中心的交互性。
英文摘要：
Information graphics are pivotal in effective information dissemination and storytelling. However, creating such graphics is extremely challenging for non-professionals, since the design process requires multifaceted skills and comprehensive knowledge. Thus, despite the many available authoring tools, a significant gap remains in enabling non-experts to produce compelling information graphics seamlessly, especially from scratch. Recent breakthroughs show that Large Language Models (LLMs), especially when tool-augmented, can autonomously engage with external tools, making them promising candidates for enabling innovative graphic design applications. In this work, we propose a LLM-centric interface with the agent GraphiMind for automatic generation, recommendation, and composition of information graphics design resources, based on user intent expressed through natural language. Our GraphiMind integrates a Textual Conversational Interface, powered by tool-augmented LLM, with a traditional Graphical Manipulation Interface, streamlining the entire design process from raw resource curation to composition and refinement. Extensive evaluations highlight our tool's proficiency in simplifying the design process, opening avenues for its use by non-professional users. Moreover, we spotlight the potential of LLMs in reshaping the domain of information graphics design, offering a blend of automation, versatility, and user-centric interactivity.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
