DeepSlide: From Artifacts to Presentation Delivery

TL;DR

DeepSlide is a human-in-the-loop multi-agent system designed to enhance presentation delivery by optimizing pacing, narrative, and rehearsal, beyond just creating visually plausible slides.

Contribution

It introduces a comprehensive system supporting the entire presentation process, including planning, grounding, rendering, and rehearsal, with a new benchmark for delivery quality.

Findings

DeepSlide improves narrative flow and pacing accuracy across 20 domains.

It matches strong baselines on artifact quality but outperforms on delivery metrics.

The dual-scoreboard benchmark separates static artifact quality from dynamic delivery excellence.

Abstract

Presentations are a primary medium for scholarly communication, yet most AI slide generators optimize the artifact (a visually plausible deck) while under-optimizing the delivery process (pacing, narrative, and presentation preparation). We present DeepSlide, a human-in-the-loop multi-agent system that supports preparing the full presentation process, from requirement elicitation and time-budgeted narrative planning, to evidence-grounded slide--script generation, attention augmentation, and rehearsal support. DeepSlide integrates (i) a controllable logical-chain planner with per-node time budgets, (ii) a lightweight content-tree retriever for grounding, (iii) Markov-style sequential rendering with style inheritance, and (iv) sandboxed execution with minimal repair to ensure renderability. We further introduce a dual-scoreboard benchmark that cleanly separates static artifact quality from dynamic delivery excellence. Across 20 domains and diverse audience profiles, DeepSlide matches strong baselines on artifact quality while consistently achieving larger gains on delivery metrics, improving narrative flow, pacing precision, and slide--script synergy with clearer attention guidance.