AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios

TL;DR

AgentVista is a comprehensive benchmark designed to evaluate multimodal agents in complex, realistic scenarios involving multi-step visual reasoning and long-horizon tool use, revealing current model limitations.

Contribution

We introduce AgentVista, a new benchmark covering diverse realistic scenarios and tool interactions, to better evaluate and advance multimodal agent capabilities.

Findings

State-of-the-art models perform poorly on complex tasks

Even the best model achieves only 27.3% accuracy

Long-horizon tool use often exceeds 25 steps

Abstract

Real-world multimodal agents solve multi-step workflows grounded in visual evidence. For example, an agent can troubleshoot a device by linking a wiring photo to a schematic and validating the fix with online documentation, or plan a trip by interpreting a transit map and checking schedules under routing constraints. However, existing multimodal benchmarks mainly evaluate single-turn visual reasoning or specific tool skills, and they do not fully capture the realism, visual subtlety, and long-horizon tool use that practical agents require. We introduce AgentVista, a benchmark for generalist multimodal agents that spans 25 sub-domains across 7 categories, pairing realistic and detail-rich visual scenarios with natural hybrid tool use. Tasks require long-horizon tool interactions across modalities, including web search, image search, page navigation, and code-based operations for both image processing and general programming. Comprehensive evaluation of state-of-the-art models exposes significant gaps in their ability to carry out long-horizon multimodal tool use. Even the best model in our evaluation, Gemini-3-Pro with tools, achieves only 27.3% overall accuracy, and hard instances can require more than 25 tool-calling turns. We expect AgentVista to accelerate the development of more capable and reliable multimodal agents for realistic and ultra-challenging problem solving.