LlamaIndex 提出智能体式 OCR，用循环解析取代传统 OCR 的一次性输出：按布局识别阅读顺序、将复杂元素智能路由到合适模型、多轮验证与自我纠错，并多模态解析图表、图像和复杂表格。主推文称前沿模型处理该任务在成本与延迟上过度设计，却仍在长尾复杂边缘案例上表现吃力。博文由 LlamaIndex 开源负责人 Logan Markewich 撰写。
OCR is the perfect example of a use case that has been dominated by legacy/brittle systems, and can be solved both accurately and cheaply by applying the right amount of agentic intelligence.
A properly tuned agentic OCR needs to dynamically apply extra compute to complex elements, review and correct failures, and create the right semantic meaning throughout the page. It's a task that frontier models are both overengineered for in terms of cost and latency, and struggle at over a long tail of complex edge cases.
Check out this blog post by @LoganMarkewich below: https://www.llamaindex.ai/blog/ocr-is-dead-long-live-agentic-ocr
OCR is dead 🪦 Long live agentic OCR! Traditional OCR makes one pass and hands back whatever text it got. Tables get flattened, charts disappear, and multi-column layouts come out scrambled. Nothing checks the output. Agentic OCR treats parsing as a loop instead: ✅ layout-aware reading order ✅ smart routing of hard elements to the right model ✅ multi-pass verification and self-correction ✅ multimodal parsing of charts, images, and complex tables Logan Markewich, LlamaIndex's Head of Open Source, wrote about what that shift looks like in practice and where it's still struggling. Link to the breakdown in the comments below.在 X 查看被引用的帖子
来源：Jerry Liu · x.com