DAIR.AI 推出 AI 论文精选集，生产环境改用 Drex Max 做研究筛选
DAIR.AI 上线了两套每日更新的论文精选集，主题是 harness 工程和递归自我改进，还能通过 MCP 直接和论文对话。做智能体开发的人可以把这个接进自己的研究工作流，省掉每天手动刷论文的时间。
DAIR.AI 的 Elvis 发布了两套 AI Paper Collections 精选集，分别聚焦 Harness Engineering（harness 工程）与 Recursive Self-Improvement（递归自我改进），每日更新，地址为 academy.dair.ai。精选集基于其自研论文筛选工具构建，用户可以通过配套的 paper chat 工具或 MCP 工具直接与论文对话。
作者同时透露，团队已将 Drex Max 用于生产环境中的研究论文分拣（research triage），并认为该模型在独立指数上的表现印证了其选择。这意味着论文筛选不再只是人工编辑，而是由模型自动化完成初筛。
对研究者和工程师而言，这两个主题（harness 工程与递归自我改进）正是当前智能体开发的前沿方向，每日更新加 MCP 接口让论文追踪可以接入自己的工作流。
We have started to use Drex Max for research triage in production, so it's good to see it hold up on an independent index. Example: x.com/omarsar0/statu… elvis @omarsar0 Introducing our new AI Paper Collections. You can now track highly recommended papers and tools for harness engineering and recursive self-improvement. Updates daily! Built on our in-house paper curation tools. You can also chat with the papers via our paper chat tool or MCP tools. Harness Engineering: academy.dair.ai/papers/collect… RSI: academy.dair.ai/papers/collect… 🔗 View Quoted Tweet📊 1 ⚡
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Drex Max, DAIR.AI, MCP and tools.
Source attribution: curated from elvis (@omarsar0). Cross-source corroboration: 2 independent sources have covered this development (including Artificial Analysis), confirming industry-wide signal strength.
- Artificial Analysis11-11 18:18Source
