SOURCE-LINKED INTELLIGENCE

The Router Within: Eliciting Native Skill Routing from a Frozen LLM

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Skills extend an LLM agent beyond its parametric knowledge, and the gain they promise rests on picking the right one. Deployed harnesses route by preloading every skill's metadata into the context, which disperses the agent's attention and caps the library size. Retrieval pipelines move the selection out of the context, but also out of the agent's capability. We show that the frozen agent LLM already carries the routing signal in its own forward passes, and that two linear maps suffice to read it out with no skill text in the context. Gavel (Glance And Verdict from a frozen LLM) reads it in tw

Read original source ↗ Open in workspace

recordType

paper

region

Global