New research from Renmin University. Treat skill selection as a harness in its own right. If you design skill routing for personal or edge a…

New research from Renmin University. Treat skill selection as a harness in its own right. If you design skill routing for personal or edge agents, this work argues that the selection layer is a first-class component you train and own, sitting alongside memory rather than inside it. The work builds a lightweight local preference harness for on-device personal agents. It keeps a cheap statistical preference learner on-device while a remote LLM handles semantic intent, and the local statistics modulate the model's skill-selection decisions rather than overriding them. Framed as a bandit-style local optimization, the decoupled design reports the lowest cumulative regret and highest test accuracy against memory-augmented agents. Paper: https://arxiv.org/abs/2606.05828 Learn to build effective AI agents in our academy: https://academy.dair.ai/

Source: DAIR.AI (X) | 2026-06-06