@ms_aifrontiers: Today we're introducing Web Skill Factory: a pipeline that turns solved web tasks into reusable, verified code. Most ag…
Summary
Microsoft AI Frontiers introduces Web Skill Factory, a pipeline that converts solved web tasks into reusable, verified code programs. Reusing the library on a WebArena subset with gpt-5.4 boosts held-out accuracy from 55% to 70% and reduces average steps from 17.1 to 14.7.
View Cached Full Text
Cached at: 08/05/26, 06:23 AM
Today we’re introducing Web Skill Factory: a pipeline that turns solved web tasks into reusable, verified code.
Most agent “skills” are notes a model rereads and reinterprets every run. Ours are programs.
On a WebArena subset with gpt-5.4, reusing the library moved accuracy on held-out instances from 55% to 70%, and cut average steps from 17.1 to 14.7.
Similar Articles
@free_ai_guides: https://x.com/free_ai_guides/status/2071666929451094227
A comprehensive guide explaining how to create reusable skills for AI coding agents, covering the SKILL.md standard adopted by major tools like OpenAI Codex and GitHub Copilot, with benchmark data showing curated skills improve pass rates by 16 points.
@omarsar0: New research from Microsoft Research I see a lot of AI engineers handwriting agent skill docs and hope they generalize.…
Microsoft Research introduces SkillOpt, a method that treats agent skill documents as trainable external state, using an optimizer model to make bounded edits validated by a held-out set. The approach achieves best or tied results across 52 evaluation cells and improves accuracy by over 23 points on GPT-5.5, with zero extra inference cost and transferable skills.
@gippp69: THIS GUY SHOWED THE MICROSOFT LOOP THAT PUSHED GPT-5.5 FROM 41% TO 80% WITHOUT RETRAINING microsoft’s skillopt paper sa…
The tweet discusses Microsoft's SkillOpt paper, which improved GPT-5.5 accuracy from 41% to 80% without retraining by using a small skills file to guide the agent.
@hnshah: https://x.com/hnshah/status/2062647149582750101
This article argues that the first AI strategy for companies should be creating a 'skill library' to capture the reusable working methods of top performers, so agents can learn the method behind tasks rather than just access data. It promotes a live webinar called Skills 101.
@oliviscusAI: MICROSOFT JUST OPEN-SOURCED SELF-EVOLVING AGENT SKILLS. it's called skillopt. skills that improve themselves the same w…
Microsoft open-sourced SkillOpt, a tool that enables AI agent skills to self-improve by automatically evaluating and rewriting their instructions, outperforming hand-crafted prompts and other optimizers with no model lock-in.