arXiv AI September 1, 2026 By Chengming Cui, Tianxin Wei, Ziyi Chen, Ruizhong Qiu, Zhichen Zeng, Zhining Liu, Xuying Ning, Duo Zhou, Jingrui He

AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs

Read the original on arXiv AI →

AdaFuse is an adaptive ensemble decoding framework for large language models that dynamically selects fusion units during generation. It uses an uncertainty-based criterion to decide when to ensemble, applying a diversity-aware scaling strategy in uncertain states while continuing direct generation when confident. Experiments on question answering, arithmetic reasoning, and machine translation show AdaFuse outperforms strong baselines with an average relative improvement of 6.88%.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 21

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

arXiv:2505. 20161v2 Announce Type: replace-cross Abstract: Effective generalization in language models depends critically on the diversity of their training data.

By Jaehun Jung, Seungju Han, Ximing Lu, Skyler Hallinan, David Acuna, Shrimai Prabhumoye, Mostafa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Yejin Choi

llms benchmarks

arXiv AI

Jul 22

Large Language Models Explore by Latent Distilling

arXiv:2604. 24927v2 Announce Type: replace-cross Abstract: Generating diverse responses is crucial for test-time scaling of large language models (LLMs), yet standard stochastic sampling mostly yields surface-level lexical variation, limiting semantic exploration.

By Yuanhao Zeng, Ao Lu, Lufei Li, Zheng Zhang, Yexin Li, Kan Ren

llms benchmarks

arXiv Computation and Language

Sep 30

MERGE: Multi-LLM Ensemble for Retrieval via Generative Enrichment

arXiv:2609.37574v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used to enrich user queries in information retrieval (IR) so that a standard retriever such as BM25 can...

By Tzu-I Ho, Yung-Yu Shih, Shang-Yu Su, Dongzhe Wang, Yun-Nung Chen

llms benchmarks

arXiv Machine Learning

Jun 15

Ensembling Sparse Autoencoders

arXiv:2505. 16077v2 Announce Type: replace Abstract: Sparse autoencoders (SAEs) are used to decompose neural network activations into human-interpretable features.

By Soham Gadgil, Chris Lin, Su-In Lee

llms

arXiv Machine Learning

Aug 12

REATS: LLM Reasoning-based Ensemble Learning for Adaptive Time Series Forecasting

arXiv:2608. 10149v1 Announce Type: new Abstract: Due to the diversity of real-world time series, no single forecasting model consistently dominates across all samples.

By Xu Zhang, Chang Xu, Hui Sun, Nan Ma, Zijian Zhang, Peng Wang, Wei Wang, Li Zhao

llms fine-tuning benchmarks safety

arXiv Computation and Language

Aug 21

EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation

arXiv:2604. 26170v2 Announce Type: replace Abstract: Adapting large language models (LLMs) to a targeted task efficiently and effectively remains a fundamental challenge.

By Ting-Wei Li, Sirui Chen, Jiaru Zou, Yingbing Huang, Tianxin Wei, Jingrui He, Hanghang Tong

llms benchmarks safety

One email a morning, machine-written

Related stories

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

Large Language Models Explore by Latent Distilling

MERGE: Multi-LLM Ensemble for Retrieval via Generative Enrichment

Ensembling Sparse Autoencoders

REATS: LLM Reasoning-based Ensemble Learning for Adaptive Time Series Forecasting

EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation