Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents

Excerpt

arXiv:2610.01892v1 Announce Type: new Abstract: Multimodal agents commonly generate free-form reasoning before each action. For small models, limited model capacity can result in lengthy reasoning that provides little useful guidance for action generation while incurring substantial inference cost. To address this challenge, we introduce Selection-based Structured Reasoning (SSR), a framework that reformulates reasoning as selection instead of open-ended generation. SSR represents recurring high