Cover Image

Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bi, Jiaxi, Luo, Tongxu, Du, Wenyu, Tang, Zhengyang, Wang, Benyou
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning from Peers in Reasoning Models
by: Luo, Tongxu, et al.
Published: (2025)

MathScale: Scaling Instruction Tuning for Mathematical Reasoning
by: Tang, Zhengyang, et al.
Published: (2024)

Do Phone-Use Agents Respect Your Privacy?
by: Tang, Zhengyang, et al.
Published: (2026)

Cut Your Losses in Large-Vocabulary Language Models
by: Wijmans, Erik, et al.
Published: (2024)

Unlocking Continual Learning Abilities in Language Models
by: Du, Wenyu, et al.
Published: (2024)

DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning
by: Chen, Xiwen, et al.
Published: (2025)

Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
by: Wang, Xu, et al.
Published: (2025)

Decoding the Ear: A Framework for Objectifying Expressiveness from Human Preference Through Efficient Alignment
by: Lin, Zhiyu, et al.
Published: (2025)

CoRT: Code-integrated Reasoning within Thinking
by: Li, Chengpeng, et al.
Published: (2025)

Pruning Minimal Reasoning Graphs for Efficient Retrieval-Augmented Generation
by: Wang, Ning, et al.
Published: (2026)

ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding
by: Zhong, Shuzhang, et al.
Published: (2024)

RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions
by: Liu, Wanlong, et al.
Published: (2024)

Parallel Scaling Law for Language Models
by: Chen, Mouxiang, et al.
Published: (2025)

Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths
by: Chia, Yew Ken, et al.
Published: (2024)

Learning from Failures in Multi-Attempt Reinforcement Learning
by: Chung, Stephen, et al.
Published: (2025)

Reasoning with Sampling: Your Base Model is Smarter Than You Think
by: Karan, Aayush, et al.
Published: (2025)

CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling
by: Tang, Zhengyang, et al.
Published: (2025)

Language Model-Driven Data Pruning Enables Efficient Active Learning
by: Azeemi, Abdul Hameed, et al.
Published: (2024)

Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs
by: Wang, Qibin, et al.
Published: (2025)

Efficient Vision-Language Reasoning via Adaptive Token Pruning
by: Li, Xue, et al.
Published: (2025)

Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training
by: Du, Wenyu, et al.
Published: (2024)

Efficient Mathematical Reasoning Models via Dynamic Pruning and Knowledge Distillation
by: Yu, Fengming, et al.
Published: (2025)

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

Structured Pruning for Diverse Best-of-N Reasoning Optimization
by: Nguyen, Hieu Trung, et al.
Published: (2025)

Native Hybrid Attention for Efficient Sequence Modeling
by: Du, Jusen, et al.
Published: (2025)

ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling
by: Huang, Chenyu, et al.
Published: (2024)

Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?
by: Yan, Kai, et al.
Published: (2025)

ParallelSpec: Parallel Drafter for Efficient Speculative Decoding
by: Xiao, Zilin, et al.
Published: (2024)

ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models
by: Lian, Long, et al.
Published: (2025)

Learn it or Leave it: Module Composition and Pruning for Continual Learning
by: Wang, Mingyang, et al.
Published: (2024)

Efficient Post-Training Pruning of Large Language Models with Statistical Correction
by: Yu, Peiqi, et al.
Published: (2026)

BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation
by: Xu, Peng, et al.
Published: (2024)

PaPaformer: Language Model from Pre-trained Parallel Paths
by: Tapaninaho, Joonas, et al.
Published: (2025)

Dynamic Vocabulary Pruning in Early-Exit LLMs
by: Vincenti, Jort, et al.
Published: (2024)

Pruning Literals for Highly Efficient Explainability at Word Level
by: Yadav, Rohan Kumar, et al.
Published: (2024)

VOCABTRIM: Vocabulary Pruning for Efficient Speculative Decoding in LLMs
by: Goel, Raghavv, et al.
Published: (2025)

Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers
by: Anagnostidis, Sotiris, et al.
Published: (2023)

On Importance of Pruning and Distillation for Efficient Low Resource NLP
by: Mirashi, Aishwarya, et al.
Published: (2024)

Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning
by: Lu, Ximing, et al.
Published: (2025)

Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning
by: Lin, Chaofan, et al.
Published: (2025)