AI Paper Atlas

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

The Avengers: A Routing Recipe for Collective Intelligence in Language Models

Yiqun Zhang, Hao Li, Chenxu Wang, Linyao Chen, Qiaosheng Zhang, Peng Ye, Shi Feng, Xinrun Wang, Jia Xu, Lei Bai, Shuyue Hu

AAAI 2026 · Large language models › Language, safety and interpretability · approach: LLM pruning and scaling data · 2 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
use Self-Consistency instead of Aggregation (ablation)Avengers · Average excluding code tasksaverage score: 56.73 -> 66.98Improved
use Self-Consistency instead of Direct (CoT) (ablation)Avengers · Average excluding code tasksaverage score: 59.19 -> 66.98Improved
use Self-Consistency instead of Model-Switch (ablation)Avengers · Average excluding code tasksaverage score: 66.42 -> 66.98No clear effect
swap embedding model (bge-m3 to text-embedding-3-large) (ablation)Avengers · 15-dataset averageaverage score: 70.28 -> 70.70No clear effect
swap clustering algorithm (BIRCH to Hierarchical) (ablation)Avengers · 15-dataset averageaverage score: 70.04 -> 70.71No clear effect
vary number of clusters K from about 14 to 140 (ablation)Avengers · 15-dataset averageaverage score: surpasses GPT-4.1/4.5 for K approximately 14 to 140No clear effect
use only 30% of data for clustering/validation (ablation)Avengers · 15-dataset averageaverage score: peaks at 0.30-0.35 test split; surpasses GPT-4.1/4.5 with 30%No clear effect
route with clustering instead of mixture-of-agentsAvengers vs MoA · 15-dataset averageaverage score: 56.70 -> 70.54Improved
clustering-based router instead of EmbedLLM on OOD dataAvengers · 5 OOD datasets averageaverage score: 69.77 -> 74.42Improved
clustering-based router instead of EmbedLLMAvengers · 15-dataset averageaverage score: 69.24 -> 70.54Improved
clustering-based router instead of Random RouterAvengers · 15-dataset averageaverage score: 49.78 -> 70.54Improved
clustering-based router instead of LLM RouterAvengers · 15-dataset averageaverage score: 64.76 -> 70.54Improved

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