Not Search, But Scan: Benchmarking MLLMs on Scan-Oriented Academic Paper Reasoning

ArXi:2603.28651v1 Announce Type: new With the rapid progress of multimodal large language models (MLLMs), AI already performs well at literature retrieval and certain reasoning tasks, serving as a capable assistant to human researchers, yet it remains far from autonomous research. The fundamental reason is that current work on academic paper reasoning is largely confined to a search-oriented paradigm centered on pre-specified targets, with reasoning grounded in relevance retrieval, which struggles to researcher-style full-document understanding, reasoning, and verification.