AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Breaking Model Lock-in: Cost-Efficient Zero-Shot LLM Routing via a Universal Latent Space

Cheng Yan, Wuyang Zhang, Zhiyuan Ning, Fan Xu, Ziyang Tao, Lu Zhang, Bing Yin, Yanyong Zhang

AAAI 2026 · Large language models › Language, safety and interpretability · approach: LLM pruning and scaling data

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
select anchor queries by D-optimality instead of random sampling (ablation)ZeroRouter · New-model onboarding, 200 anchors, Max-Accreward: 0.27 -> 0.39Improved
select anchors by difficulty only (Diff-based) instead of D-optimality (ablation)ZeroRouter · New-model onboarding, 200 anchors, Max-Accreward: 0.39 -> 0.24Hurt
select anchors by discrimination only (Disc-based) instead of D-optimality (ablation)ZeroRouter · New-model onboarding, 200 anchors, Max-Accreward: 0.39 -> 0.28Hurt
use task-aware difficulty (alpha^T b) for anchor selection instead of D-optimality (ablation)ZeroRouter · New-model onboarding, 200 anchors, Max-Accreward: 0.39 -> 0.32Hurt
use D-optimality anchors on mean reward vs random sampling (ablation)ZeroRouter · New-model onboarding, 200 anchors, meanreward: -0.25 -> -0.11Improved
use ZeroRouter instead of GraphRouter, FORC, RouteLLM, Model-SAT on smaller LLMs5 smaller LLMs router · ID and OOD, three policiesmean reward: -0.14 -> 0.00Improved
use ZeroRouter instead of GraphRouter on larger LLMs5 larger LLMs router · ID and OOD, three policiesmean reward: -0.07 -> 0.05Improved
use ZeroRouter instead of strongest baseline on OOD Max-Acc with larger LLMs5 larger LLMs router · OOD, Max-Accreward: 0.62 -> 0.68Improved
use ZeroRouter instead of Model-SAT on OOD Max-Acc with smaller LLMs5 smaller LLMs router · OOD, Max-Accreward: 0.57 -> 0.59No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy