DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation

ACL ARR 2026 January Submission4273 Authors

Keywords: Presentation Generation, LLM Agents, Multi-Agent Collaboration, Environment-Grounded Reflection, Trajectory Synthesis

Abstract:

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 \model remains highly competitive at substantially lower cost.

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: LLM/AI agents, interactive and collaborative generation, multimodal applications

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources

Languages Studied: English, Chinese

Submission Number: 4273