Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology
This work addresses the problem of evaluating and improving visual grounded reasoning for AI researchers, though it is incremental as it builds on existing models and benchmarks.
The authors tackled the lack of benchmarks for evaluating visual grounded reasoning in models by proposing TreeBench, a diagnostic benchmark with 405 challenging visual question-answering pairs, where advanced models like OpenAI-o3 score only 54.87% accuracy. They also introduced TreeVGR, a training paradigm that improves performance on benchmarks like V* Bench (+16.8) and TreeBench (+13.4), demonstrating that traceability enhances vision-grounded reasoning.
Models like OpenAI-o3 pioneer visual grounded reasoning by dynamically referencing visual regions, just like human "thinking with images". However, no benchmark exists to evaluate these capabilities holistically. To bridge this gap, we propose TreeBench (Traceable Evidence Evaluation Benchmark), a diagnostic benchmark built on three principles: (1) focused visual perception of subtle targets in complex scenes, (2) traceable evidence via bounding box evaluation, and (3) second-order reasoning to test object interactions and spatial hierarchies beyond simple object localization. Prioritizing images with dense objects, we initially sample 1K high-quality images from SA-1B, and incorporate eight LMM experts to manually annotate questions, candidate options, and answers for each image. After three stages of quality control, TreeBench consists of 405 challenging visual question-answering pairs, even the most advanced models struggle with this benchmark, where none of them reach 60% accuracy, e.g., OpenAI-o3 scores only 54.87. Furthermore, we introduce TreeVGR (Traceable Evidence Enhanced Visual Grounded Reasoning), a training paradigm to supervise localization and reasoning jointly with reinforcement learning, enabling accurate localizations and explainable reasoning pathways. Initialized from Qwen2.5-VL-7B, it improves V* Bench (+16.8), MME-RealWorld (+12.6), and TreeBench (+13.4), proving traceability is key to advancing vision-grounded reasoning. The code is available at https://github.com/Haochen-Wang409/TreeVGR.