Copertina

Towards Better RL Training Data Utilization via Second-Order Rollout

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yang, Zhe, Wang, Yudong, Li, Rang, Sui, Zhifang
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Enhancing Reliability across Short and Long-Form QA via Reinforcement Learning
di: Wang, Yudong, et al.
Pubblicazione: (2025)

Exploring Activation Patterns of Parameters in Language Models
di: Wang, Yudong, et al.
Pubblicazione: (2024)

A Probabilistic Inference Scaling Theory for LLM Self-Correction
di: Yang, Zhe, et al.
Pubblicazione: (2025)

Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs
di: Yang, Zhe, et al.
Pubblicazione: (2024)

Not All Demonstration Examples are Equally Beneficial: Reweighting Demonstration Examples for In-Context Learning
di: Yang, Zhe, et al.
Pubblicazione: (2023)

Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding
di: Iso, Hayate, et al.
Pubblicazione: (2026)

Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers
di: Ma, Wenhan, et al.
Pubblicazione: (2025)

Plug-and-Play Training Framework for Preference Optimization
di: Ma, Jingyuan, et al.
Pubblicazione: (2024)

CoLT: Reasoning with Chain of Latent Tool Calls
di: Zhu, Fangwei, et al.
Pubblicazione: (2026)

SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative Rollouts
di: Liu, Bingshuai, et al.
Pubblicazione: (2025)

From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling
di: Chen, Zhengyu, et al.
Pubblicazione: (2025)

Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow
di: Xi, Haocheng, et al.
Pubblicazione: (2026)

Reducing Hallucinations in Entity Abstract Summarization with Facts-Template Decomposition
di: Zhu, Fangwei, et al.
Pubblicazione: (2024)

RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data Selection
di: Yang, Yixin, et al.
Pubblicazione: (2025)

Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR
di: Xu, Haobo, et al.
Pubblicazione: (2026)

Reinforcement Pre-Training
di: Dong, Qingxiu, et al.
Pubblicazione: (2025)

Chain-of-Thought Tokens are Computer Program Variables
di: Zhu, Fangwei, et al.
Pubblicazione: (2025)

Towards Harmonized Uncertainty Estimation for Large Language Models
di: Li, Rui, et al.
Pubblicazione: (2025)

Language Models Encode the Value of Numbers Linearly
di: Zhu, Fangwei, et al.
Pubblicazione: (2024)

Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones?
di: Yang, Zhe, et al.
Pubblicazione: (2024)

Stable and Efficient Single-Rollout RL for Multimodal Reasoning
di: Liu, Rui, et al.
Pubblicazione: (2025)

Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts
di: Luo, Sijia, et al.
Pubblicazione: (2026)

Self-Boosting Large Language Models with Synthetic Preference Data
di: Dong, Qingxiu, et al.
Pubblicazione: (2024)

FSM: A Finite State Machine Based Zero-Shot Prompting Paradigm for Multi-Hop Question Answering
di: Wang, Xiaochen, et al.
Pubblicazione: (2024)

Can Large Multimodal Models Uncover Deep Semantics Behind Images?
di: Yang, Yixin, et al.
Pubblicazione: (2024)

HINT: Helping Ineffective Rollouts Navigate Towards Effectiveness
di: Wang, Xinyi, et al.
Pubblicazione: (2025)

Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding
di: Xia, Heming, et al.
Pubblicazione: (2024)

TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents
di: Djuhera, Aladin, et al.
Pubblicazione: (2026)

HistLens: Mapping Idea Change across Concepts and Corpora
di: Jing, Yi, et al.
Pubblicazione: (2026)

SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine
di: Wang, Xiaochen, et al.
Pubblicazione: (2024)

AlpaGasus: Training A Better Alpaca with Fewer Data
di: Chen, Lichang, et al.
Pubblicazione: (2023)

Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees
di: Li, Kun, et al.
Pubblicazione: (2026)

Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming
di: Li, Rui, et al.
Pubblicazione: (2025)

$V_{0.5}$: Generalist Value Model as a Prior for Sparse RL Rollouts
di: Zhang, Yi-Kai, et al.
Pubblicazione: (2026)

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training
di: Wei, Lai, et al.
Pubblicazione: (2025)

PeriodicLoRA: Breaking the Low-Rank Bottleneck in LoRA Optimization
di: Meng, Xiangdi, et al.
Pubblicazione: (2024)

Training Language Model to Critique for Better Refinement
di: Yu, Tianshu, et al.
Pubblicazione: (2025)

Are Full Rollouts Necessary for On-Policy Distillation?
di: Zhang, Yaocheng, et al.
Pubblicazione: (2026)

MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs
di: Qian, Yusu, et al.
Pubblicazione: (2024)

TeaMs-RL: Teaching LLMs to Generate Better Instruction Datasets via Reinforcement Learning
di: Gu, Shangding, et al.
Pubblicazione: (2024)