GTA

The 'GTA' dataset is a benchmark used to evaluate the performance of vision language models in multimodal tool-use reasoning tasks.

Papers using GTA (4)

GTA: A Benchmark For General Tool Agents2024 · 2 citesReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents2026MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning2025Multi-modal Agent Tuning: Building A Vlm-driven Agent For Efficient Tool Usage2024