Sign InOpen Brain
arXivPaperNeeds Review

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

Gavel routes skills from a frozen model’s internal states without loading skill text into context. It suggests large skill libraries may need model-native selection rather than metadata-heavy prompts.

arXiv · Sep 14, 2026
Open Source Open MarkdownOpen JSON
Source Summary

Gavel reads skill-routing signals from a frozen LLM using **two trained linear maps**. A glance scores the full library from mid-layer states and prebuilt skill banks; a verdict resumes shortlisted forward passes and combines likelihood with a yes/no judgment.

Practical Implication

Harness authors should benchmark routing separately from skill execution, especially when skills become relevant mid-run. This design keeps skill descriptions out of the active context and avoids external rerankers with **1.2B–16B parameters**.

Agent-Ready Context
Gavel reads skill-routing signals from a frozen LLM using **two trained linear maps**. A glance scores the full library from mid-layer states and prebuilt skill banks; a verdict resumes shortlisted forward passes and combines likelihood with a yes/no judgment.

Harness authors should benchmark routing separately from skill execution, especially when skills become relevant mid-run. This design keeps skill descriptions out of the active context and avoids external rerankers with **1.2B–16B parameters**.

On Qwen3-32B, Gavel leads compared pipelines by **up to 13.4 points** on written tasks and **up to 21.9 points** for mid-rollout skill needs. The claims span three public benchmarks plus a new simulated-trajectory benchmark, so production generality remains open.
Connected Context · Feed7 Judgment

Gavel shifts progressive skill discovery inside the frozen model: compact learned probes shortlist skills without placing the entire catalog in context or adding a large reranker, including when relevance appears mid-rollout. It strengthens the case for evaluating routing as its own subsystem, while leaving governance, execution safety, model-change reevaluation, and production transfer outside the reported routing gains.

Skills are new features: Building Skill-Centric Harness — Yogendra Miraje, FactSetGavel offers a concrete routing mechanism for the skill-centric harness, while FactSet’s account supplies the surrounding requirements—versioning, model-specific evaluation, access control, and governance—that routing accuracy alone does not cover.500 Skills, Zero Fine-Tuning: LinkedIn's Playbook for AI Agents — Ajay Prakash, LinkedInLinkedIn demonstrates progressive discovery through search and meta-tools at large catalog scale; Gavel proposes a contrasting native-model shortlist-and-verdict pipeline that keeps skill descriptions out of active context.Agents Without Code: Skills, YAML, and Filesystems Replaced Python — Philipp Schmid, Google DeepMindThe low-code agent pattern reduces bespoke orchestration but leaves evaluation to builders; Gavel makes routing evaluation especially necessary because skill selection is learned separately from execution.zhaoxuya520/reverse-skillThe security router shows why selection must be paired with authorization and evidence stages; Gavel may improve which skill is chosen, but its reported design does not replace external controls around risky execution.
Context Map
agentcoding#skills#tool-use#context-engineering
Uncertainty
On Qwen3-32B, Gavel leads compared pipelines by **up to 13.4 points** on written tasks and **up to 21.9 points** for mid-rollout skill needs. The claims span three public benchmarks plus a new simulated-trajectory benchmark, so production generality remains open.