AI Paper Atlas

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

ICL-Router: In-Context Learned Model Representations for LLM Routing

Chenxu Wang, Hao Li, Yiqun Zhang, Linyao Chen, Jianhao Chen, Ping Jian, Qiaosheng Zhang, Shuyue Hu

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Pruning and circuits in LLMs · 17 citations (OpenAlex)

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
add query reconstruction training (stage 1) (ablation)ICL-Router · In-distribution (5 benchmarks, average)accuracy: 74.01 -> 76.30Improved
add query reconstruction training (stage 1) (ablation)ICL-Router · OOD (5 benchmarks, average)accuracy: 64.06 -> 66.47Improved
use a larger embedding model (0.3B to 8B) (ablation)ICL-Router · In-distribution (5 benchmarks, average)accuracy: 74.45 -> 76.30Improved
use a larger embedding model (0.3B to 8B) (ablation)ICL-Router · OOD (5 benchmarks, average)accuracy: 64.55 -> 66.47Improved
increase in-context exemplars from 100 to 500 (ablation)ICL-Router · In-distribution (5 benchmarks, average)accuracy: 74.94 -> 76.30Improved
increase in-context exemplars from 500 to 1000 (ablation)ICL-Router · In-distribution (5 benchmarks, average)accuracy: 76.30 -> 75.75Hurt
increase in-context exemplars from 500 to 1000 (ablation)ICL-Router · OOD (5 benchmarks, average)accuracy: 66.47 -> 65.71Hurt
add new LLMs to the pool without retraining the routerICL-Router · In-distribution (5 benchmarks, average)accuracy: 76.3 -> 79.9Improved
add new LLMs to the pool without retraining the routerICL-Router · OOD (5 benchmarks, average)accuracy: 66.4 -> 69.9Improved
add new LLMs to the poolMODEL-SAT · In-distribution and OODaccuracyMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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