AI Paper Atlas

Research map / Large language models / Reasoning and chain of thought

Mixture-of-Trees: Learning to Select and Weigh Reasoning Paths for Efficient LLM Inference

Yangbo Wei, Zhen Huang, Shaoqiang Lu, Junhong Qian, Dongge Qin, Ting Jung Lin, WEI W. XING, Chen Wu, Lei He

AAAI 2026 · Large language models › Reasoning and chain of thought · approach: Efficient and adaptive thinking · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes Mixture-of-Trees (MoT), which combines sparse expert activation via a learned gate with tree-based reasoning so that only the most relevant reasoning-tree experts, of varying model capacity, are run per problem for efficient LLM inference.

Problem

Efficient LLM inference for reasoning tasks, where running full tree-structured reasoning with large models on every problem is costly.

Approach

Applies sparse mixture-of-experts style gating at the level of reasoning trees: a learned gate activates only the most relevant expert trees per problem, and experts use models of different capacities matched to task complexity.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add sparse activation of expert trees (ablation)MoT · HotpotQALLM calls: 98.45 -> 33.67Improved
add sparse activation of expert trees (ablation)MoT · HotpotQAaccuracy: 82.8 -> 81.4Hurt
add early stopping with shared baseline tree (ablation)MoT · HotpotQALLM calls: 33.67 -> 23.91Improved
add early stopping with shared baseline tree (ablation)MoT · HotpotQAaccuracy: 81.4 -> 79.2Hurt
add specialized expert trees (ablation)MoT · HotpotQAaccuracy: 79.2 -> 81.1Improved
replace FoT with MoT (gated experts, debate)MoT · AIME 2024 (GPT-4o-mini)accuracy: 33.3 -> 40.0Improved
replace FoT with MoTMoT · GSM8K (GPT-4o-mini)LLM calls: 32.32 -> 19.21Improved
replace FoT with MoTMoT · MMLU (GPT-4o-mini)accuracy: 91.6 -> 93.9Improved
lower activation threshold tau from 0.9 to 0.7 (ablation)MoT · GSM8K/AIMEaccuracyImproved
lower activation threshold tau from 0.7 to 0.5 (ablation)MoT · GSM8K/AIMEaccuracyNo clear effect
scale expert pool from 8 to 64 (ablation)MoT · GSM8K, MATH, MMLUaccuracyMixed

Experimental setup

Builds on: mixture of experts tree-of-thoughts

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