Primary sourceAravind Srinivas
View sourceEvent ·Multi-source
Perplexity 计划构建多模型多智能体框架,打造自动化研究员
Perplexity CEO Aravind Srinivas 在 X 上表示,公司将持续构建一个 multi model 与 multi agent 框架,用于处理开放性问题回答、实验设计、假设构建等复杂任务。该框架的思路是让多个智能体并行地对假设进行测试与 ablation(消融实验),再逐步迭代优化预测与答案。这条推文同时列出了多条推文约 1597 次浏览、5 次点赞的数据,说明其引发一定讨论。最终目标是做出一个 automated researcher(自动化研究员),把科研中假设、验证、修正的循环交给智能体完成。这延续了行业里 multi agent 协作研究系统的方向,与 OpenAI 的 deep research 类产品思路相近,区别在于 Perplexity 强调多模型混用和并行消融的 harness 设计。
Current read
Perplexity 的 CEO 亲自说了路线图:多模型加多智能体并行跑假设、做消融实验,目标是自动化研究员。想了解 agent 框架怎么用于科研流程的开发者,这条推文信息量不大但方向明确,适合配合 deep research 类产品一起对比着看。
11 sources29° AI heatLast updated 2026/11/17 16:41:34
Evidence
11 sourcesRelated source 1Perplexity
View sourceRelated source 2Aadit Sheth
View sourceRelated source 3阿里云 Alibaba Cloud
View sourceRelated source 4Rest of World
View sourceRelated source 5techcrunch
View sourceRelated source 6IT之家
View sourceRelated source 7TestingCatalog
View sourceRelated source 8The Rundown AI
View sourceRelated source 9Tibor Blaho
View sourceRelated source 10lmarena.ai
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.