PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback
Recent efforts have aimed to automate scientific diagram generation from paper content (Lin et al., 2026; Zhu et al., 2026a). However, fully satisfying an author's visual and communicative preferences in a single turn is challenging: in our formative user study (N = 14), all participants requested further revisions after viewing an initial draft, and 86% of them rated the refined diagrams as more satisfactory. Despite the clear demand, the multi-turn workflow remains largely underexplored. To bridge this gap, we present MTPaperBananaBench, a benchmark for multi-turn diagram generation containing 292 images annotated with 3,518 user requirements. To reduce expensive human studies and enabl...
| Authors | Xueqing Wu, Ashwin Balasubramanian, Bingxuan Li et al. |
|---|---|
| Primary category | cs.CL |
| Published | 31 August 2026 |
| Last updated at source | 31 August 2026 |
Connected in the knowledge graph
- xqwu/MTPaperBananaBenchDataset · cited by
Models and datasets referencing this paper
- xqwu/MTPaperBananaBenchDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.