# AutoTailor filters auto-generated web APIs from 1,283 candidates to 33

DAIR.AI highlighted AutoTailor, a paper from Microsoft Research and colleagues that turns web trajectories into parameterized browser-automation APIs and filters them down to 33. On 106 WebArena Postmill tasks, those APIs with a ReAct fallback reached 90.6% correctness versus 87.5% for ReAct alone.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-11-10T06:57:00.000Z
Query date (America/Los_Angeles): 2026-11-09

HTML: https://didcodexreset.com/news/c155c451e4274e238fa72fcb.html

Content language: en
Localization state: sameLanguage

Source: DAIR.AI · Published 9/21/2026, 10:33:31

DAIR.AI highlighted **AutoTailor**, a paper from Microsoft Research and colleagues, as relevant to auto-generating MCP tools from agent trajectories. AutoTailor turns web trajectories into parameterized browser-automation APIs, then applies a quality filter that drops APIs with the wrong granularity or duplicate function and a usage filter that keeps APIs likely to be needed, taking **1,283** candidates down to **87**. Online, it watches task outcomes, adds APIs for recurring gaps, and prunes unused ones, ending at **33**.

On **106 WebArena Postmill** tasks, the 33 APIs with a ReAct fallback reached **90.6%** correctness against **87.5%** for ReAct alone. Request-token cost dropped **57.8%** and latency **29.4%**. Without the fallback, accuracy matched the unfiltered set while using **94.9%** fewer request tokens. The paper is at [academy.dair.ai](https://academy.dair.ai/papers/autotailor-automatic-user-aligned-capability-selection-and-adaptation-for-web-ag-2609.13548).

Tags: AutoTailor, Microsoft Research, Web Agents, WebArena

[View original post](https://x.com/dair_ai/status/2102087979099717799)