Cover Image

Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Haobo, Chen, Sirui, Qiu, Ruizhong, Yan, Yuchen, Luo, Chen, Cheng, Monica, He, Jingrui, Tong, Hanghang
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Harnessing Consistency for Robust Test-Time LLM Ensemble
by: Zeng, Zhichen, et al.
Published: (2025)

TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models
by: Chen, Lingjie, et al.
Published: (2026)

EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation
by: Li, Ting-Wei, et al.
Published: (2026)

The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning
by: Jiang, Titong, et al.
Published: (2025)

Think Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning Models
by: Xiang, Yang, et al.
Published: (2025)

KVPruner: Structural Pruning for Faster and Memory-Efficient Large Language Models
by: Lv, Bo, et al.
Published: (2024)

Subspace Alignment for Vision-Language Model Test-time Adaptation
by: Zeng, Zhichen, et al.
Published: (2026)

GradMAP: Faster Layer Pruning with Gradient Metric and Projection Compensation
by: Liu, Hao, et al.
Published: (2026)

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation
by: Chen, Xinrui, et al.
Published: (2025)

Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning
by: Bandari, Abhinav, et al.
Published: (2024)

Exploring Multi-Temperature Strategies for Token- and Rollout-Level Control in RLVR
by: Zhuang, Haomin, et al.
Published: (2025)

Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models
by: Li, Jianwei, et al.
Published: (2023)

Evolutionary Negative Module Pruning for Better LoRA Merging
by: Cao, Anda, et al.
Published: (2026)

Geometric-disentangelment Unlearning
by: Zhou, Duo, et al.
Published: (2025)

NutePrune: Efficient Progressive Pruning with Numerous Teachers for Large Language Models
by: Li, Shengrui, et al.
Published: (2024)

Think Before You Prune: Self-Reflective Structured Pruning for Reasoning Language Models
by: Wang, Ziyan, et al.
Published: (2025)

The Unlearnability Phenomenon in RLVR for Language Models
by: Chen, Yulin, et al.
Published: (2026)

Recursive Multi-Agent Systems
by: Yang, Xiyuan, et al.
Published: (2026)

Gradient Compressed Sensing: A Query-Efficient Gradient Estimator for High-Dimensional Zeroth-Order Optimization
by: Qiu, Ruizhong, et al.
Published: (2024)

Saffron-1: Safety Inference Scaling
by: Qiu, Ruizhong, et al.
Published: (2025)

MI-PRUN: Optimize Large Language Model Pruning via Mutual Information
by: Zhang, Hao, et al.
Published: (2026)

STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning
by: Lee, Jaeseong, et al.
Published: (2024)

Ask, and it shall be given: On the Turing completeness of prompting
by: Qiu, Ruizhong, et al.
Published: (2024)

Pruning as a Domain-specific LLM Extractor
by: Zhang, Nan, et al.
Published: (2024)

Finding Transformer Circuits with Edge Pruning
by: Bhaskar, Adithya, et al.
Published: (2024)

PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths
by: Chen, Boyu, et al.
Published: (2025)

Leveraging KV Similarity for Online Structured Pruning in LLMs
by: Lee, Jungmin, et al.
Published: (2025)

Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR
by: Kim, Soeun, et al.
Published: (2026)

Prune4Web: DOM Tree Pruning Programming for Web Agent
by: Zhang, Jiayuan, et al.
Published: (2025)

IG-Pruning: Input-Guided Block Pruning for Large Language Models
by: Qiao, Kangyu, et al.
Published: (2025)

Latent Collaboration in Multi-Agent Systems
by: Zou, Jiaru, et al.
Published: (2025)

AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs
by: Cui, Chengming, et al.
Published: (2026)

DLP: Dynamic Layerwise Pruning in Large Language Models
by: Chen, Yuli, et al.
Published: (2025)

You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning
by: Sengupta, Ayan, et al.
Published: (2025)

Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning
by: Zou, Jiaru, et al.
Published: (2025)

Pruning General Large Language Models into Customized Expert Models
by: Zhao, Yirao, et al.
Published: (2025)

Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning
by: Zhao, Shangziqi, et al.
Published: (2025)

PruneTIR: Inference-Time Tool Call Pruning for Effective yet Efficient Tool-Integrated Reasoning
by: Zhang, Luan, et al.
Published: (2026)

Adaptive Computation Pruning for the Forgetting Transformer
by: Lin, Zhixuan, et al.
Published: (2025)

Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study
by: Yu, Shuo, et al.
Published: (2024)