Great paper from Microsoft Research and colleagues.

This is a AI post classified by Jev as AI agents (research), kept by the AI Radar because it carries real work, not commentary.

Great paper from Microsoft Research and colleagues. If you auto-generate MCP tools from agent trajectories, this one is worth your time. AutoTailor turns web trajectories into parameterized browser-automation APIs and then filters them. A quality filter drops APIs with the wrong granularity or duplicate function, and a usage filter keeps the ones likely to be needed. That takes 1,283 candidates down to 87. Online, it watches task outcomes, adds APIs for recurring gaps and prunes ones that go unused, ending at 33. On 106 WebArena Postmill tasks, the 33 APIs with a ReAct fallback reach 90.6

Posted by DAIR.AI (132.6k followers) 1 h ago · 11 likes · 2.3k views · view the original post on X. Kept by the AI Radar as AI agents. Tools mentioned: academy.dair.ai.

More AI work like this

• "Our AI agents have already done 17,000 conversations this year. And booked 600+… — @jasonlk
• Open sourced "Jev " that runs 50x faster own Jarvis running locally now on mac 1GB RAM.… — @0x0SojalSec
• Banger paper on self-evolving ontologies for agents. — @omarsar0
• 有人做了一个"星际争霸"AI 对战测试（Brood War Bench），让当下主流大模型互相打即时战略，结果所有模型的水平都没超过新手。 — @dotey
• this is literally f**king insane — @gippp69
• Hopped on a Virtual Claude workshop this morning with @AnthropicAI and @cinkotweets to… — @JJEnglert
• Or, you can work on Omarchy Linux, which is especially made to be extremely extensible… — @mark_k
• Today we're excited to share Strands Harness. Strands Harness makes it easier to build… — @MarcJBrooker

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 39.7k posts from 5k X accounts over the last 14 days, 1.6k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 18:40 UTC. Full method.