Cover Image

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Jinghui, Wang, Shaojie, Cui, Yinghan, Chen, Xuxing, Wang, Chao, Huang, Liang, Tang, Can, Zhang, Xiaojiang, Peng, Junyi, Wan, Li, Zhang, Haotian, Chen, Bin
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Schedule-Level Shared-Prefix Reuse for LLM RL Training
by: Li, Pengbo, et al.
Published: (2026)

SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM
by: Zhang, Xiaojiang, et al.
Published: (2025)

Prefix Grouper: Efficient GRPO Training through Shared-Prefix Forward
by: Liu, Zikang, et al.
Published: (2025)

CoDec: Prefix-Shared Decoding Kernel for LLMs
by: Wang, Zhibin, et al.
Published: (2025)

SeamlessFlow: A Trainer Agent Isolation RL Framework Achieving Bubble-Free Pipelines via Tag Scheduling
by: Wang, Jinghui, et al.
Published: (2025)

Accelerating Direct Preference Optimization with Prefix Sharing
by: Wang, Franklin, et al.
Published: (2024)

Bifurcated Attention: Accelerating Massively Parallel Decoding with Shared Prefixes in LLMs
by: Athiwaratkun, Ben, et al.
Published: (2024)

From Meta-Thought to Execution: Cognitively Aligned Post-Training for Generalizable and Reliable LLM Reasoning
by: Wang, Shaojie, et al.
Published: (2026)

Accelerating Suffix Jailbreak attacks with Prefix-Shared KV-cache
by: Wang, Xinhai, et al.
Published: (2026)

How to Select Pre-Trained Code Models for Reuse? A Learning Perspective
by: Bi, Zhangqian, et al.
Published: (2025)

From Implicit to Explicit: Token-Efficient Logical Supervision for Mathematical Reasoning in LLMs
by: Wang, Shaojie, et al.
Published: (2026)

Marconi: Prefix Caching for the Era of Hybrid LLMs
by: Pan, Rui, et al.
Published: (2024)

LLM Query Scheduling with Prefix Reuse and Latency Constraints
by: Dexter, Gregory, et al.
Published: (2025)

Fully First-Order Methods for Decentralized Bilevel Optimization
by: Wang, Xiaoyu, et al.
Published: (2024)

Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training
by: Wang, Xi, et al.
Published: (2026)

Structure-Guided Adversarial Training of Diffusion Models
by: Yang, Ling, et al.
Published: (2024)

Joint Training Across Multiple Activation Sparsity Regimes
by: Wang, Haotian
Published: (2026)

TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration
by: Zhu, Haowei, et al.
Published: (2026)

ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows
by: Wang, Penghao, et al.
Published: (2025)

PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention
by: Wang, Haonan, et al.
Published: (2025)

An Augmented Lagrangian Method for Training Recurrent Neural Networks
by: Wang, Yue, et al.
Published: (2024)

PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization
by: Chen, Mengzhao, et al.
Published: (2024)

Exploring Dynamic Properties of Backdoor Training Through Information Bottleneck
by: Liu, Xinyu, et al.
Published: (2025)

KAT-Coder Technical Report
by: Zhan, Zizheng, et al.
Published: (2025)

VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs
by: Lu, Keer, et al.
Published: (2024)

From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation
by: Wang, Jiahao, et al.
Published: (2026)

FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models
by: So, Junhyuk, et al.
Published: (2023)

Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony
by: Lu, Han, et al.
Published: (2025)

Can LLMs Threaten Human Survival? Benchmarking Potential Existential Threats from LLMs via Prefix Completion
by: Cui, Yu, et al.
Published: (2025)

Regurgitative Training: The Value of Real Data in Training Large Language Models
by: Zhang, Jinghui, et al.
Published: (2024)

AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse
by: Yu, Zichao, et al.
Published: (2025)

sEMG-Based Joint Angle Estimation via Hierarchical Spiking Attentional Feature Decomposition Network
by: Zhou, Xin, et al.
Published: (2024)

Accelerating Compound LLM Training Workloads with Maestro
by: Yuan, Xiulong, et al.
Published: (2026)

Training-free Diffusion Acceleration with Bottleneck Sampling
by: Tian, Ye, et al.
Published: (2025)

Chain-of-Models Pre-Training: Rethinking Training Acceleration of Vision Foundation Models
by: Fan, Jiawei, et al.
Published: (2026)

Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes
by: Setlur, Amrith, et al.
Published: (2026)

Agentic Critical Training
by: Liu, Weize, et al.
Published: (2026)

Lost in Literalism: How Supervised Training Shapes Translationese in LLMs
by: Li, Yafu, et al.
Published: (2025)

Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCache
by: Cui, Bowen, et al.
Published: (2026)

LoongTrain: Efficient Training of Long-Sequence LLMs with Head-Context Parallelism
by: Gu, Diandian, et al.
Published: (2024)