Seg-ReSearch: Segmentation with Interleaved Reasoning and External Search

Segmentation based on language has been a popular topic in computer vision. While recent advances in multimodal large language models (MLLMs) have endowed segmentation systems with reasoning capabilities, these efforts remain confined by the frozen internal knowledge of MLLMs, which limits their potential for real-world scenarios that involve up-to-date information or domain-specific concepts. In this work, we propose \textbf{Seg-ReSearch}, a novel segmentation paradigm that overcomes the knowledge bottleneck of existing approaches. By enabling interleaved reasoning and external search, Seg-ReSearch empowers segmentation systems to handle dynamic, open-world queries that extend beyond the frozen knowledge of MLLMs. To effectively train this capability, we introduce a hierarchical reward design that harmonizes initial guidance with progressive incentives, mitigating the dilemma between sparse outcome signals and rigid step-wise supervision. For evaluation, we construct OK-VOS, a challenging benchmark that explicitly requires outside knowledge for video object segmentation. Experiments on OK-VOS and two existing reasoning segmentation benchmarks demonstrate that our Seg-ReSearch improves state-of-the-art approaches by a substantial margin. Code and data is available at https://github.com/iSEE-Laboratory/Seg-ReSearch.

While modern visual models can locate specific objects in images and videos, their capabilities are typically limited by the fixed knowledge they were originally trained on. When asked to identify a newly released product or domain-specific concept, these systems fail because they lack access to up-to-date or external information. To break this bottleneck, we introduce Seg-ReSearch, a novel paradigm that allows the AI to actively browse the internet during its visual reasoning process. This system can autonomously search for the missing real-world knowledge it needs to guide its visual understanding. This approach brings us closer to intelligent visual assistants that can adapt and help us navigate an ever-changing real world.