用 Tavily 加 Nemotron 3 Ultra 搭建论文研究 Agent，24 行代码 10 秒筛出本周 top5 论文
I just ran a paper-research agent on an open stack and had this week's top 5 papers on agent memory ...
24 行 Python 就能搭一个自动读 arXiv 的研究 agent，搜索用 Tavily、排序用 Nemotron 3 Ultra，每层都能换，新手照着走一遍就能上手。
作者用 Tavily 拉取过去 7 天的 arXiv 论文，再由 NVIDIA Nemotron 3 Ultra 在 Nebius Token Factory 上阅读并排序，约 10 秒得到本周 5 篇 agent memory 主题论文。整个流程是 24 行 Python，走 OpenAI 兼容 API，试用成本为零。文中还提到 Nebius AI Builder Program 提供首日 400 美元以上额度，覆盖 Token Factory、Tavily 及合作方。模型层和搜索层均可替换，其余代码不用改。
I just ran a paper-research agent on an open stack and had this week's top 5 papers on agent memory ...
I just ran a paper-research agent on an open stack and had this week's top 5 papers on agent memory in my terminal in about 10 seconds. How does it work? I used Tavily to pull the last 7 days of arXiv. NVIDIA Nemotron 3 Ultra, served on Nebius Token Factory, reads and ranks them. It's 24 lines of Python on an OpenAI-compatible API. It cost me nothing to try. You can build this too! Here is how: The new Nebius AI Builder Program gives you $400+ in credits and discounts on day one, across Token Factory, Tavily, and launch partners, plus runnable blueprints and free courses built with NVIDIA. What I like most is that every layer is swappable. Change the model or the search layer, and the rest keeps working. Walkthrough in the video. Join for free here: devtoolsacademy.link/elv Thanks to Nebius for collaborating on this post. Your browser does not support the video tag. 🔗 View on Twitter 💬 6 🔄 3 ❤️ 12 👀 2491 📊 9 ⚡
