If you’re building an “agent over your PDFs” in 2026, one of the most underrated things you can do is to provide exact grounding back to the…

If you’re building an “agent over your PDFs” in 2026, one of the most underrated things you can do is to provide exact grounding back to the source document for any agentic answers. Specifically, showing the exact word, line, or region that the answer came from. Frontier vision models do a terrible job at this. They have a hard time predicting exact bounding boxes over region, tying it back to the source answer, and surfacing it as context in a cost-effective and accurate manner. Dedicated VLM-based document OCR/extraction tools like LlamaParse are a lot better at visual grounding and specifically tying it to extracted outputs. One of our main evaluation areas in ExtractBench, our recently released real-world benchmark, is to evaluate the visual grounding capabilities of document extraction. ExtractBench: https://www.extractbench.ai/ If you want to give LlamaParse a shot, come check it out: https://cloud.llamaindex.ai/ Media Most document extraction APIs can't tell you where a value came from. For ExtractBench, we scored grounding strictly: a field only counts if the value AND its citation are correct, word-level box at IoU 0.5. A perfect box around a wrong value earns nothing. Results: VLMs and codi…

Related

• This week we launched the world's most accurate document extraction agent over real-world documents. Introducing LlamaExtract Agentic Plus …
• Most AI pipelines are only as good as the data we provide them with, and that usually means PDFs or other unstructured documents. Contracts,…
• Agents + file sandboxes are all in the range in 2026 🤖🗃️ This is a nifty reference implementation by @itsclelia showing you how to run you…
• LiteParse runs anywhere, including inside agent runtimes. To prove it, we built an email processing assistant using @flueai (the agentic fra…

Source: Jerry Liu (X) | 2026-08-18