AI 中文总结
PosterMELD是模板条件化多智能体海报生成流水线，可导出可编辑PPTX和PNG，在621篇论文实验中PRR达81.3%，成本仅为Codex+Skill的3.5%，性能优于P2P、PosterGen等方法。
AI 中文摘要
科学海报构建将长文本多模态论文压缩为可读、可编辑的画布。现有系统仅对完成的输出评分以掩盖请求级失败；直接图像生成不可编辑元素，而编码智能体工作流成本高昂。PosterMELD是一个模板条件化多智能体流水线：容量感知插槽在渲染前指导写作，确定性门控加视觉语言模型（VLM）审查将失败路由至有界修复。每个被接受的请求导出可编辑的PowerPoint（PPTX）和便携式网络图形（PNG）产物；明确的设计控制产生同一论文的变体。在621篇论文上，打印就绪率（PRR）统计通过几何、可读性、资产完整性和明显事实错误检查的请求，原生可编辑性单独报告。冻结的VLM为打印就绪输出分配有条件的工艺-和谐-表现力（CHE）分数。PosterMELD达到81.3%的PRR，是P2P的3.4倍、PosterGen的5.2倍，且在具有多个打印就绪输出的生成方法中获得最高的有条件CHE。原生可编辑性和明确设计控制的平均成本为每个请求0.38美元，是Codex+Skill的3.5%。代码和资源可在此https URL获取。
英文摘要
Scientific poster construction compresses a long multimodal paper into a readable, editable canvas. Existing systems hide request-level failures by scoring only completed outputs; direct image generation is not element-editable, while coding-agent workflows are costly. PosterMELD is a template-conditioned multi-agent pipeline: capacity-aware slots guide writing before rendering, and deterministic gates plus vision-language model (VLM) review route failures to bounded repair. Each accepted request exports editable PowerPoint (PPTX) and Portable Network Graphics (PNG) artifacts; explicit design controls yield same-paper variants. Across 621 papers, Print-Ready Rate (PRR) counts requests passing geometric, readability, asset-integrity, and obvious-factual-error checks, with native editability reported separately. A frozen VLM assigns conditional Craftsmanship-Harmony-Expressiveness (CHE) scores to print-ready outputs. PosterMELD attains 81.3% PRR, 3.4 times P2P's rate and 5.2 times PosterGen's, and the highest conditional CHE among generated methods with multiple print-ready outputs. Native editability and explicit design controls are retained at a mean cost of USD 0.38 per request, 3.5% of Codex+Skill's. Code and resources are available at https://github.com/Shannon4Science/PosterMELD.
Comments9 pages, 5 figures, and 4 tables. Code and resources are available at https://github.com/Shannon4Science/PosterMELD
