Tag
Microsoft proposes the SkillOpt method, which treats documents as trainable parameters. By optimizing natural language documents without modifying weights, it improves model performance. It achieves 52 consecutive wins across 6 benchmarks, with GPT-5.5 improving by 23.5 points and Claude Code by 19.1 points.
This MUSE-Autoskill paper focuses on how an Agent manages an entire skill library, placing skills into a complete lifecycle: creation, memory, management, evaluation, and re-optimization.
Microsoft open-sourced SkillOpt, a method that treats markdown skill files like neural network parameters to train AI agents without modifying model weights, using learning rates, validation checks, minibatches, and epochs.
A tip for Codex users to implement agent research papers directly into their Codex environment using goal mode and local config, with SkillOpt as an example that improved a GPT-5.5 agent by +24.8 points.