Cover Image

Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qu, Yun, Wang, Qi, Mao, Yixiu, Hu, Vincent Tao, Ommer, Björn, Ji, Xiangyang
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models
by: Mao, Yixiu, et al.
Published: (2026)

Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models
by: Qu, Yun, et al.
Published: (2026)

RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning
by: Mao, Yixiu, et al.
Published: (2026)

Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning
by: Mao, Yixiu, et al.
Published: (2025)

Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning
by: Zou, Heming, et al.
Published: (2025)

Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression
by: Mao, Yixiu, et al.
Published: (2024)

Doubly Mild Generalization for Offline Reinforcement Learning
by: Mao, Yixiu, et al.
Published: (2024)

Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments
by: Qu, Yun, et al.
Published: (2025)

Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning
by: Qu, Yun, et al.
Published: (2024)

[MASK] is All You Need
by: Hu, Vincent Tao, et al.
Published: (2024)

Optimizing Reasoning Efficiency through Prompt Difficulty Prediction
by: Zhao, Bo, et al.
Published: (2025)

Online Finetuning Decision Transformers with Pure RL Gradients
by: Luo, Junkai, et al.
Published: (2026)

VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal RL
by: Hu, Zengjie, et al.
Published: (2025)

VAO: Validation-Aligned Optimization for Cross-Task Generative Auto-Bidding
by: Lv, Yiqin, et al.
Published: (2025)

Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning
by: Mahrooghi, Ilia, et al.
Published: (2026)

Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model
by: Wu, Jiahao, et al.
Published: (2026)

Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
by: Qu, Yun, et al.
Published: (2026)

Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions
by: Baumann, Stefan Andreas, et al.
Published: (2024)

Model Predictive Task Sampling for Efficient and Robust Adaptation
by: Wang, Qi, et al.
Published: (2025)

SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling
by: Zhang, Yiqi, et al.
Published: (2026)

DARA: Few-shot Budget Allocation in Online Advertising via In-Context Decision Making with RL-Finetuned LLMs
by: Song, Mingxuan, et al.
Published: (2026)

An Empirical Study on the Effectiveness of Incorporating Offline RL As Online RL Subroutines
by: Su, Jianhai, et al.
Published: (2025)

ZigMa: A DiT-style Zigzag Mamba Diffusion Model
by: Hu, Vincent Tao, et al.
Published: (2024)

Accelerating RL for LLM Reasoning with Optimal Advantage Regression
by: Brantley, Kianté, et al.
Published: (2025)

RL-Finetuned LLMs for Privacy-Preserving Synthetic Rewriting
by: Shi, Zhan, et al.
Published: (2025)

Can Past Experience Accelerate LLM Reasoning?
by: Pan, Bo, et al.
Published: (2025)

DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models
by: Shen, Yi, et al.
Published: (2025)

Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning
by: Wagenmaker, Andrew, et al.
Published: (2025)

Diffusion Models and Representation Learning: A Survey
by: Fuest, Michael, et al.
Published: (2024)

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies
by: Chen, Jiaqi, et al.
Published: (2025)

PromptWise: Online Learning for Cost-Aware Prompt Assignment in Generative Models
by: Hu, Xiaoyan, et al.
Published: (2025)

Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction Uncertainty
by: Cho, Yeseul, et al.
Published: (2025)

RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMs
by: Fernandez, Nigel, et al.
Published: (2025)

Shorter Thoughts, Same Answers: Difficulty-Scaled Segment-Wise RL for CoT Compression
by: Tian, Ye, et al.
Published: (2026)

OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning
by: Yue, Sheng, et al.
Published: (2024)

Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers
by: Yan, Kai, et al.
Published: (2024)

Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning
by: Liang, Sirui, et al.
Published: (2025)

CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models
by: Li, Shuozhe, et al.
Published: (2026)

RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video
by: Prestel, Ulrich, et al.
Published: (2026)

Can you Finetune your Binoculars? Embedding Text Watermarks into the Weights of Large Language Models
by: Elhassan, Fay, et al.
Published: (2025)