Search papers, labs, and topics across Lattice.
ArcDeck, a multi-agent framework, tackles paper-to-slide generation by explicitly modeling the source paper's discourse structure via a discourse tree and global commitment document. This structured narrative reconstruction, refined through iterative multi-agent critique and revision, ensures preservation of high-level intent. Experiments on the new ArcBench dataset show that this approach significantly improves narrative flow and logical coherence compared to direct summarization methods.
Forget bullet-point vomit: ArcDeck uses AI agents to reverse-engineer the *story* of a research paper, turning it into a coherent slide deck.
We introduce ArcDeck, a multi-agent framework that formulates paper-to-slide generation as a structured narrative reconstruction task. Unlike existing methods that directly summarize raw text into slides, ArcDeck explicitly models the source paper's logical flow. It first parses the input to construct a discourse tree and establish a global commitment document, ensuring the high-level intent is preserved. These structural priors then guide an iterative multi-agent refinement process, where specialized agents iteratively critique and revise the presentation outline before rendering the final visual layouts and designs. To evaluate our approach, we also introduce ArcBench, a newly curated benchmark of academic paper-slide pairs. Experimental results demonstrate that explicit discourse modeling, combined with role-specific agent coordination, significantly improves the narrative flow and logical coherence of the generated presentations.
