AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

Narrative-Driven Paper-to-Slide Generation via ArcDeck

Tarik Can Ozden, SACHIDANAND VISHNUKUMAR SARMINI, Furkan Horoz, Ozgur Kara, Junho Kim, James Rehg

ECCV 2026 · Multi-agent systems and games › LLM agents · approach: Agent data synthesis and behavior studies · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Discourse Parser (ablation)ArcDeck outline generation · ArcBench outline ablation (Narrative Flow, 0-10 scale)Narrative Flow: 7.50 -> 9.70Improved
add Global Commitment (ablation)ArcDeck outline generation · ArcBench outline ablation (Narrative Flow, 0-10 scale)Narrative Flow: 7.52 -> 9.70Improved
add Narrative Refinement Loop (ablation)ArcDeck outline generation · ArcBench outline ablation (Narrative Flow, 0-10 scale)Narrative Flow: 8.68 -> 9.70Improved
add Discourse Parser (pairwise preference) (ablation)ArcDeck · ArcBench pairwise narrative flowwin rate vs ablated: 89.1Improved
add Global Commitment (pairwise preference) (ablation)ArcDeck · ArcBench pairwise narrative flowwin rate vs ablated: 94.5Improved
add Narrative Refinement Loop (pairwise preference) (ablation)ArcDeck · ArcBench pairwise narrative flowwin rate vs ablated: 61.8Improved
run Narrative Refinement Loop for 3 iterations instead of 1 (ablation)ArcDeck outline · ArcBench NRL study (5 papers)Narrative Flow: 4.18 -> 7.34Improved
run Narrative Refinement Loop for 2 iterations instead of 1 (ablation)ArcDeck outline · ArcBench NRL study (5 papers)Narrative Flow: 4.18 -> 7.00Improved
use ArcDeck instead of SlideGen (ablation)GPT-4o backbone · ArcBench VLM Q/A quiz (open) Hardaccuracy (%): 66.15 -> 72.63Improved
use ArcDeck instead of SlideGenQwen3-VL-32B backbone · ArcBench VLM Q/A quiz (open) Hardaccuracy (%): 76.57 -> 83.22Improved
use ArcDeck instead of SlideGen (narrative flow A/B)Qwen3-VL-32B backbone, GPT-5 judge · ArcBench A/B narrative flowwin rate (%): 48.5No clear effect
use ArcDeck instead of SlideGen (narrative flow A/B)GPT-5 backbone, GPT-5 judge · ArcBench A/B narrative flowwin rate (%): 50.6No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy