VisDocAgentBench: Benchmarking Agents for Visually Rich Document Retrieval
Visually rich documents encode relevance through language, layout, structured visual elements, and corpus context, yet retrieval is typically evaluated by one-shot query--page matching. Agentic-search benchmarks usually score downstream question answering or report generation, leaving document ranking under iterative evidence acquisition underexplored. We introduce VisDocAgentBench, a closed-corpus benchmark comparing static and agentic retrieval under a shared ranked-output contract. It contains 2,375 pages from 100 documents and 120 unique-target queries balanced across direct, one-bridge, and two-bridge evidence structures. Relation-preserving construction yields semantic, relational, ...
| Authors | Lexiang Hu, Yanzhao Zhang, Mingxin Li et al. |
|---|---|
| Primary category | cs.IR |
| Published | 18 August 2026 |
| Last updated at source | 18 August 2026 |
Models and datasets referencing this paper
- hulx2002/VisDocAgentBenchDataset
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 Information may be incomplete or out of date.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.