Microsoft researchers developed SkillOpt, a method that treats AI agent skill files as trainable parameters outside frozen target models, enabling controlled optimization through bounded text edits an…
An AI developer built a Guard Extension with 158 lines of code to enforce skill-editing rules, but a creator's three questions revealed the system was flawed and unnecessary. The developer realized th…
On June 18, 2026, open-weight model GLM-5.2 scored 74.4% on FrontierSWE, trailing Claude Opus 4.8 by one point, signaling the collapse of the scale myth as smaller models rival frontier performance. T…
Microsoft and three Chinese universities developed SkillOpt, a method that optimizes instruction documents for AI agents using principles from traditional model training. A simple Markdown file booste…
The U.S. government cut off access to Anthropic's Claude Fable 5 and Mythos 5 on June 13, triggering a global suspension and a trust crisis in frontier AI models. Simultaneously, the agent infrastruct…
Microsoft has released SkillOpt, an open-source framework that automatically optimizes AI agent skills by treating instruction documents as trainable objects that evolve based on performance feedback.…
A coding implementation on Microsoft SkillOpt demonstrated an instrumented workflow for prompt optimization, including repository setup, model configuration, and a full optimization loop with rollout,…
Microsoft Research has released SkillLens, an open-source framework designed as a "microscope" for analyzing how AI agents absorb and utilize skills. The framework provides a complete pipeline for ext…
SkillOpt introduces a method for improving AI agent performance by treating skills as external state, allowing a frozen agent to be evaluated on scored batches while a separate optimizer model propose…