PulseAugur
实时 04:32:45

Perplexity AI trains Qwen model for optimized search and tool use

Perplexity AI has developed a new model by post-training on top of Qwen, achieving optimal accuracy-cost trade-offs. This model is specifically engineered for enhanced search capabilities and simultaneous tool usage, integrating the tool call router for unified functionality. This advancement aims to improve the efficiency and effectiveness of AI-driven search and task execution. AI

影响 Enhances search and tool-calling capabilities, potentially improving AI assistant efficiency.

排序理由 A research announcement detailing a new model post-trained on an existing foundation model.

在 X — Aravind Srinivas (Perplexity) 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Perplexity AI trains Qwen model for optimized search and tool use

报道来源 [1]

  1. X — Aravind Srinivas (Perplexity) TIER_1 English(EN) · AravSrinivas ·

    We’ve post trained a model on top of Qwen that achieves Pareto optimality on accuracy-cost curves.

    We’ve post trained a model on top of Qwen that achieves Pareto optimality on accuracy-cost curves. Unlike our previous post trained models, this model has been trained to be good at search and tool calls simultaneously, allowing us to unify the tool call router and