The paper introduces HOPE, a second‑order pruning method for Mixture‑of‑Experts language models that accounts for cooperative interactions between experts. Unlike first‑order methods such as REAP, HOPE derives an objective that provably bounds pruning error and is shown to outperform baselines across three large MoE models, multiple calibration sets, and diverse benchmarks, especially at high pruning rates and on agentic tasks. The results demonstrate that preserving expert interactions allows aggressive compression with minimal performance loss on complex workloads.
By Alex M. Tseng, Prannay Kaul, Luca Zancato, Wei Xia, Stefano Soatto
arXiv:2603. 18492v3 Announce Type: replace Abstract: Mixture-of-Experts (MoE) language models increase parameter capacity without proportional per-token computation, yet deployment still requires storing the full expert pool, making expert pruning important for reducing memory and serving overhead.
By Zongfang Liu, Guangyi Chen, Shengkun Tang, Yifan Shen, Huan Wang, Xin Yuan
arXiv:2609.25809v1 Announce Type: new
Abstract: Fine-grained mixture-of-experts (MoE) architectures have become a mainstream design for open-weight LLMs, with hundreds of experts and increasingly man...
By Yuanteng Chen, Qiwei Lai, Chen Tianqi, Peisong Wang, Yuantian Shao, Nanxin Zeng, Zhilei Liu, Chuangyi Li, Jing Liu, Jian Cheng
arXiv:2610.27123v1 Announce Type: cross
Abstract: Mixture-of-Experts (MoE) models reduce computation through sparse expert activation, but deployment still requires storing a large number of expert p...
By Jelena Markovic-Voronov, Petros Prastakos, Kayhan Behdin, Jincheng Cao, Zhipeng Wang, Shayan Mohajer Hamidi, Yuanda Xu, Zhengze Zhou, Wenhui Zhu, Rahul Mazumder
arXiv:2607. 01710v1 Announce Type: new Abstract: Sparsely activated Mixture-of-Experts (MoE) language models contain substantial structured redundancy among routed experts, but pruning them without downstream calibration data remains challenging.
By Yongqin Zeng, Sicheng Pan, Jiale Wang, Hai-tao Zheng, Hong-Gee Kim, Chunxia Ma, XiuTeng Zhou
Sparsely activated Mixture-of-Experts (MoE) language models contain substantial structured redundancy among routed experts, but pruning them without downstream calibration data remains challenging. Existing expert-pruning methods typically rely on a single aggregated importance score, which can bias the retained set toward experts favored by dominant calibration patterns.
Dynamic Expert Pruning for Multi-Agent Systems introduces DEP, a method that generates a per-request mask of experts based on an agent’s system and task prompts. Unlike static pruning, DEP uses a lightweight predictor trained on workflow transcripts to activate only the experts needed for each specific request, requiring no per-configuration calibration. Experiments across various tasks, models, and MoE architectures show DEP outperforms static pruning and merging baselines, especially when few experts are retained, and it generalizes to unseen workflows.
By Jabin Koo, Soheil Abbasloo, Sungjae Lee, Jungseul Ok
arXiv:2606.15716v2 Announce Type: replace
Abstract: Mixture-of-Experts (MoE) language models reduce per-token computation through sparse expert activation, yet deployment still requires storing the f...
By Zongfang Liu, Jinghui Zhang, Zijian Ma, Guangyi Chen, Xin Yuan
arXiv:2504.04342v2 Announce Type: replace
Abstract: Scaling up model parameters and training data consistently improves the performance of large language models (LLMs), but at the cost of rapidly gro...
By Ayan Sengupta, Siddhant Chaudhary, Tanmoy Chakraborty
arXiv:2606. 15716v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models reduce per-token computation through sparse expert activation, yet deployment still requires storing the full expert pool, making one-shot expert pruning a practical approach for reducing memory usage.
By Zongfang Liu, Jinghui Zhang, Zijian Ma, Guangyi Chen, Xin Yuan
The paper examines how expert pruning—removing low‑importance experts in Mixture‑of‑Experts models—fails when the router is over‑dispersed, a condition caused by aggressive load‑balancing that spreads tokens nearly uniformly across experts. In this regime, traditional importance signals from router probabilities collapse, making perplexity an unreliable predictor of downstream accuracy; for example, the lowest‑perplexity pruning on gpt‑oss‑20B harms mathematical reasoning while the highest‑perplexity pruning preserves it. To address this, the authors introduce Minimax Expert Score Allocation (MESA), a domain‑aware method that iteratively boosts scores for the most affected domain, achieving minimal worst‑case degradation across domains and outperforming baseline pruning strategies on multiple benchmarks while reducing memory usage.
By Berkcan Kapusuzoglu, Connor Pryor, Sangwoo Cho, Supriyo Chakraborty, Shi-Xiong Zhang, Sambit Sahu, Milind Naphade
arXiv:2606. 27866v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models scale model ability with sparsely activated experts, making this architecture a standard recipe for modern large models.
By Fan Mo, Yuxuan Han, Geng Zhang, Wangbo Zhao, Yang You