Perplexity 已在其计算机编排系统内增强了其深度研究功能，使其能够将复杂问题分解为子任务。然后，这些子任务会被路由到 20 多个不同的前沿 AI 模型，并由 Gemini 等专业代理处理特定的研究需求。这种由“搜索即代码”方法驱动的新方法旨在提高准确性、分析深度和引用质量，从而交付可直接用于工作的报告、演示文稿和仪表板。 AI
影响 增强了 Perplexity 从多个 AI 模型合成信息的能力，可能提高用户的研究效率。
排序理由 Perplexity 是一个集成多个 AI 模型的产品，而不是一个前沿模型实验室。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
<p>Deep Research now lives inside Perplexity Computer, breaking hard questions into subtasks and routing across 20+ frontier models.</p> <p>The post <a href="https://www.marktechpost.com/2026/06/11/perplexity-moves-deep-research-into-computer-routing-research-subtasks-across-20-f…
Perplexity has moved Deep Research into Computer, its multi-model orchestration system. The upgrade breaks complex questions into subtasks and routes them across over 20 frontier models. BrowseComp accuracy jumped from 40.7% to 83.8%. https://www. marktechpost.com/2026/06/11/pe r…
🤖 Perplexity Upgrades Deep Research with Multi-Model Orchestration Perplexity has upgraded Deep Research to route complex questions across 20+ frontier models, improving accuracy and citation quality. This significant enhancement moves Deep Research into Computer, Perplexity's ad…