Microsoft Research By Yifan Yang, Xuemei Gao, Qi Dai, Bei Liu, Kai Qiu, Dongdong Chen, Chong Luo

SkillOpt: Agent skills as trainable parameters

Read the original on Microsoft Research →

AI agents often fail because their instructions, or skills, are manually modified with no guarantee of improvement. Learn how SkillOpt turns skill editing into a training process, making agent behavior more reliable without changing model weights.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Microsoft Research.

Hugging Face Trending Papers
Jun 3

AIP: A Graph Representation for Learning and Governing Agent Skills

Agent Skills today consist largely of free-form prose requiring the agent to read, interpret, and re-derive how to act in every session. This imposes two compounding costs: reduced reliability on implementation-heavy tasks, and difficulty in skill creation and improvement, since editing prose is a fragile process that both humans and agents struggle with, particularly for domain-specific procedural knowledge underrepresented in model training.