SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories

While MLLMs have demonstrated impressive image understanding capabilities, they still struggle with pixel-level comprehension, limiting their practical applications. Current evaluation tasks such as VQA and visual grounding remain too coarse to assess fine-grained pixel comprehension accurately. Although segmentation is foundational for pixel-level understanding, existing methods often require MLLMs to generate implicit tokens, decoded through external pixel decoders. This approach disrupts the MLLM's text output space, potentially compromising language capabilities and reducing flexibility and extensibility while failing to reflect the model's intrinsic pixel-level understanding. Thus, we introduce the Human-Like Mask Annotation Task (HLMAT), a new paradigm where MLLMs mimic human annotators using interactive segmentation tools. Modelling segmentation as a multi-step Markov Decision Process, HLMAT enables MLLMs to iteratively generate textbased click points, achieving high-quality masks without architectural changes or implicit tokens. Through this setup, we develop SegAgent, a model fine-tuned on human-like annotation trajectories, which achieves performance comparable to SoTA methods and supports additional tasks like mask refinement and annotation filtering. HLMAT provides a protocol for assessing fine-grained pixel understanding in MLLMs and introduces a vision-centric, multistep decision-making task that facilitates the exploration of MLLMs' visual reasoning abilities. Our adaptations of policy improvement method StaR and PRM guided tree search further enhance model robustness in complex segmentation tasks, laying a foundation for future advancements in finegrained visual perception and multi-step decision-making for MLLMs. Code can be found at https://github . com/aim-uofa/SegAgent.