選擇式結構化推理：邁向高效多模態搜尋智能體
Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents
研究提出選擇式結構化推理（SSR）框架，讓多模態智能體從預設推理候選中選擇，而非進行開放式生成。在七個多模態搜尋基準、2B 和 4B 模型上的評估中，SSR 的平均成功率與同等規模的領先搜尋智能體相若。它將每回合推理延遲降低超過 90%，每題模型推理總延遲降低 28-54%。
Published on Oct 1
Authors:
,
,
,
,
,
,
,
,
,
,
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-level reasoning as pre-specified, reusable natural-language candidates. At each turn, the model selects from these reasoning candidates based on their likelihoods given the current context, without requiring an auxiliary task head. Using pre-specified reasoning traces enables parallel scoring, where teacher-forced prefilling computes token likelihoods concurrently within and across candidates using a shared context KV cache. We evaluate SSR on seven multimodal search benchmarks using 2B and 4B models. Across multiple reinforcement learning objectives and supervised fine-tuning, SSR delivers significant efficiency gains without sacrificing task performance. SSR achieves an average success rate competitive with leading search agents of the same scale, while reducing per-turn reasoning latency by over 90% and total per-question model inference latency by 28-54%. Project page: https://zfy0314.github.io/ssr-webpage/.
View arXiv page View PDF Project page GitHub Add to collection
Get this paper in your agent:
hf papers read 2610.01892
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.01892 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.01892 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.01892 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源：HuggingFace Daily Papers（社區熱門論文） · huggingface.co