DeepPresenter: 基于环境的反思以实现代理演示生成
DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation
AI总结:
DeepPresenter通过自主规划和渲染中间幻灯片艺术来支持长周期优化,利用环境感知状态进行反馈驱动的改进,实现超越固定流程的演示生成。
摘要:
演示生成需要深入内容研究、连贯的视觉设计以及基于观察的迭代优化。然而,现有演示代理往往依赖预定义的工作流和固定模板。为解决此问题,我们提出了DeepPresenter,一种能够适应多样化用户意图、实现有效反馈驱动优化并超越固定流程的代理框架。具体而言,DeepPresenter自主规划、渲染和修订中间幻灯片艺术,以支持基于环境观察的长周期优化。此外,与依赖内部信号(如推理轨迹)的自我反思不同,我们的基于环境的反思将生成过程条件于感知艺术状态(如渲染的幻灯片),使系统能够在执行过程中识别和纠正特定演示问题。在覆盖多样化演示生成场景的评估集上,DeepPresenter实现了最先进的性能,且经过微调的9B模型在显著降低成本的情况下仍保持高度竞争力。我们的项目可在:https://github.com/icip-cas/PPTAgent 获取。
英文摘要:
Presentation generation requires deep content research, coherent visual design, and iterative refinement based on observation. However, existing presentation agents often rely on predefined workflows and fixed templates. To address this, we present DeepPresenter, an agentic framework that adapts to diverse user intents, enables effective feedback-driven refinement, and generalizes beyond a scripted pipeline. Specifically, DeepPresenter autonomously plans, renders, and revises intermediate slide artifacts to support long-horizon refinement with environmental observations. Furthermore, rather than relying on self-reflection over internal signals (e.g., reasoning traces), our environment-grounded reflection conditions the generation process on perceptual artifact states (e.g., rendered slides), enabling the system to identify and correct presentation-specific issues during execution. Results on the evaluation set covering diverse presentation-generation scenarios show that DeepPresenter achieves state-of-the-art performance, and the fine-tuned 9B model remains highly competitive at substantially lower cost. Our project is available at: https://github.com/icip-cas/PPTAgent
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。