AI Paper Atlas

Research map / Large language models / Agents, code and math

Skill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills

Justin Chen, Sukwon Yun, Elias Stengel-Eskin, Tianlong Chen, Mohit Bansal

ICML 2026 · Large language models › Agents, code and math · approach: Inductive and abstract reasoning evaluation

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 task-specific aggregator instead of random aggregator (ablation)Skill-MoE · MMLU-Proaccuracy (%): 52.29 -> 63.71Improved
use task-specific aggregator instead of adaptive instance-level aggregator (ablation)Skill-MoE · MMLU-Proaccuracy (%): 57.12 -> 63.71Improved
use task-specific aggregator instead of adaptive instance-level aggregator (ablation)Skill-MoE · GPQA Diamondaccuracy (%): 58.01 -> 57.78No clear effect
recruit experts via model profiles instead of random experts (task-specific aggregator) (ablation)Skill-MoE · GPQA Diamondaccuracy (%): 31.82 -> 57.78Improved
use task-specific aggregator instead of majority vote on recruited experts (ablation)Skill-MoE · GPQA Diamondaccuracy (%): 53.54 -> 57.78Improved
recruit with skill-based model profile instead of fixed top-3 experts (ablation)Skill-MoE · GPQA Diamondaccuracy (%): 52.86 -> 57.78Improved
use top-5 instead of top-3 fixed experts (ablation)fixed top-k recruiting · GPQA Diamondaccuracy (%): 52.86 -> 47.68Hurt
use skill-based recruiting instead of 3 random experts (ablation)Skill-MoE · GPQA Diamondaccuracy (%): 42.61 -> 57.78Improved
add trimming of rare experts (under 5% of selections) (ablation)Skill-MoE · GPQA Diamondaccuracy (%): 55.26 -> 57.78Improved
add trimming of rare experts (under 5% of selections) (ablation)Skill-MoE · MMLU-Proaccuracy (%): 63.94 -> 63.71No clear effect
add three rounds of multi-agent discussion before the task-specific aggregator (ablation)Skill-MoE · MMLU-Proaccuracy (%): 63.71 -> 63.83No clear effect
add three rounds of discussion before the task-specific aggregator (ablation)Skill-MoE · GPQA Diamondaccuracy (%): 57.78 -> 57.72No 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