Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents

Apple Machine LearningOctober 15, 2026en

Apple Machine Learning

AI Global Wire

Multimodal agents commonly generate freeform 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-level reasoning as pre-specified, reusable natural-language candidates. At each turn, the model selects from the reasoning candidates based on their…

This is a short summary published by AI Global Wire. The full article is owned and hosted by Apple Machine Learning — open it there to read it in full.

• Verktyg
• Agenter