TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning

ICLR 2026 Conference Submission13207 Authors

Keywords: Benchmark, Thinking with Images

TL;DR: We propose a benchmark for Thinking with Images reasoning

Abstract:

The frontier of visual reasoning is shifting toward models like OpenAI o3, which can intelligently create and operate tools to transform images for problem-solving, also known as thinking-\textit{with}-images in chain-of-thought. Yet existing benchmarks fail to fully capture this advanced capability. Even Visual Search, the most common benchmark for current thinking-\textit{with}-images methods, tests only basic operations such as localization and cropping, offering little insight into more complex, dynamic, and tool-dependent reasoning.
We introduce \textbf{TIR-Bench}, a comprehensive benchmark for evaluating agentic thinking-with-images across 13 diverse tasks, each requiring novel tool use for image processing and manipulation in chain-of-thought. We evaluate 22 multimodal large language models (MLLMs), from leading open-sourced and proprietary models to those with explicit tool-use augmentation. Results show that TIR-Bench is universally challenging, and strong performance requires genuine thinking-with-images capabilities. Finally, we present a pilot study comparing direct versus agentic fine-tuning.

Primary Area: datasets and benchmarks

Submission Number: 13207