Skip to content
Book Open access

AutoDavis: Automatic and Dynamic Evaluation Protocol of Large Vision-Language Models on Visual Question-Answering

Aug 2026 · Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 · 0 citations · 9 references

TL;DR

AutoDavis is introduced, a first-of-its-kind automatic and dynamic evaluation protocol that enables on-demand benchmarking of LVLMs across specific capability dimensions and shows effectiveness and reliability, offering a new paradigm for dynamic benchmarking of multimodal intelligence.

Abstract

Large Vision-Language Models (LVLMs) have become essential for advancing the integration of visual and linguistic information. While existing benchmarks have laid a solid foundation for evaluation, they are often static, resource-intensive to build, and limited in adaptability. In comparison, automatic evaluation has shown promise in the textual domain, but the visual modality remains far less explored. To advance this frontier, in this work, we introduce AutoDavis, a first-of-its-kind automatic and dynamic evaluation protocol that enables on-demand benchmarking of LVLMs across specific capability dimensions. AutoDavis leverages text-to-image models to generate relevant image samples and then utilizes LVLMs to orchestrate visual question-answering (VQA) tasks, completing the evaluation process efficiently and flexibly. To ensure data diversity, our framework employs a hierarchical aspect-driven generation process enhanced with semantic graph-based constraints. To safeguard reliability, the framework incorporates a self-validation mechanism to detect and correct errors, along with an error-driven adjustment module to mitigate potential bias. Through an extensive evaluation of 11 popular LVLMs across five demanded user inputs (i.e., evaluation capabilities), the framework shows effectiveness and reliability, offering a new paradigm for dynamic benchmarking of multimodal intelligence. View website for code and data.

Read PDF

Similar papers

Preprint Jul 2026

Incentivizing Vision Language Models to Search for Long Video Question Answering

We introduce VSeek, an agentic framework that transforms long-video question answering (LVQA) from a passive, single-pass perception task into a multi-turn retrieval process. VSeek utilizes a natural language-driven search to identify relevant context within long videos and is post-trained with reinforcement learning (RL) to jointly formulate targeted search queries and reason over retrieved clips for LVQA. While RL post-training has revolutionized reasoning in symbolic domains such as mathematics and code, its application to long-video understanding remains hindered by a lack of verified rewards. To ensure that the retrieved context is relevant, we propose a novel neuro-symbolic approach that bridges open-ended natural language with discrete visual verification. Specifically, complex user queries are compiled into formal temporal logic specifications for systematically decomposing natural language questions into a definitive checklist of required atomic visual primitives, such as key objects and activities, along with their temporal ordering. These systematically derived grounding events provide the critical feedback signal for RL post-training, enabling dense, verifiable rewards based on the successful retrieval of these specific visual elements rather than relying entirely on outcome-only answer accuracy. By explicitly optimizing for this verifiable evidence-seeking behavior, VSeek improves Pass@1 scores by up to 8% and Pass@4 scores by 15% on long-video understanding benchmarks compared to base models. We open-source our code at https://utaustin-swarmlab.github.io/VSeek.

Harsh Goel, S. Sharan, Sahil Shah et al. · 1 citation
Preprint Jul 2026

Comparative Study of Domain-adapted VLMs for General Document Visual Question Answering

The findings demonstrate that while large pretrained VLMs possess strong zero-shot baselines for structured layouts, their performance strongly decreases on visually complex layouts of infographics and slides, and that visual understanding is the main bottleneck for DocVQA, not a lack of knowledge from the VLMs.

Miguel Lopez-Duran, Elena Marrero, Julian Fiérrez et al. · 2 citations
Open access 2026

Challenging the Abilities of Large Language Models in Italian: a Community Initiative

CALAMITA is conceived as a rolling benchmark, enabling continuous integration of new tasks and models, and argues that this combination offers a blueprint for other languages and communities seeking inclusive and rigorous LLM evaluation practices.

Malvina Nissim, Danilo Croce, V. Patti et al. · 0 citations
Preprint Jul 2026

CRAG-MM-Diagnostics: Enabling Stage-Wise Analysis of Knowledge-Intensive VQA

This work introduces CRAG-MM-Diagnostics, a diagnostic benchmark with stage-wise data annotations that isolate 1) language-based visual grounding, 2) object identification, and 3) knowledge retrieval and reasoning from the KI-VQA pipeline, and proposes a grounded bimodal RAG pipeline that integrates a visual grounding module to crop targets before image retrieval.

Hanseok Oh, Parishad BehnamGhader, Benno Krojer et al. · 0 citations
Book Open access Jul 2026

Eagle: Leveraging Operations Documents for Comprehensive Benchmark Question Generation

Eagle, a comprehensive benchmarking framework tailored for evaluating OpsLLMs, delivers a deployable foundation for advancing large-model applications in AIOps and open-source the framework and dataset to foster community adoption and reproducibility.

Yuhe Liu, Changhua Pei, Hang Wang et al. · 0 citations