Cover Image

Can GRPO Help LLMs Transcend Their Pretraining Origin?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ni, Kangqi, Tan, Zhen, Liu, Zijie, Li, Pingzhi, Chen, Tianlong
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

QuantMoE-Bench: Examining Post-Training Quantization for Mixture-of-Experts
by: Li, Pingzhi, et al.
Published: (2024)

DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillation
by: Li, Pingzhi, et al.
Published: (2025)

Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion
by: Tan, Zhen, et al.
Published: (2026)

DLO: Dynamic Layer Operation for Efficient Vertical Scaling of LLMs
by: Tan, Zhen, et al.
Published: (2024)

Leave It to the Experts: Detecting Knowledge Distillation via MoE Expert Signatures
by: Li, Pingzhi, et al.
Published: (2025)

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs
by: Itzhak, Itay, et al.
Published: (2025)

Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
by: Li, Pingzhi, et al.
Published: (2023)

Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design
by: Zhang, Mohan, et al.
Published: (2025)

Can Stories Help LLMs Reason? Curating Information Space Through Narrative
by: Javadi, Vahid Sadiri, et al.
Published: (2024)

Can LLMs Help Uncover Insights about LLMs? A Large-Scale, Evolving Literature Analysis of Frontier LLMs
by: Park, Jungsoo, et al.
Published: (2025)

PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches
by: Khan, Rana Muhammad Shahroz, et al.
Published: (2024)

7B Fully Open Source Moxin-LLM/VLM -- From Pretraining to GRPO-based Reinforcement Learning Enhancement
by: Zhao, Pu, et al.
Published: (2024)

ORAL: Prompting Your Large-Scale LoRAs via Conditional Recurrent Diffusion
by: Khan, Rana Muhammad Shahroz, et al.
Published: (2025)

Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO
by: Chen, Peter, et al.
Published: (2025)

Adaptive-Boundary-Clipping GRPO: Ensuring Bounded Ratios for Stable and Generalizable Training
by: Liu, Chi, et al.
Published: (2026)

ExGRPO: Learning to Reason from Experience
by: Zhan, Runzhe, et al.
Published: (2025)

Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO
by: Zeng, Zhiyuan, et al.
Published: (2026)

Fine-tuning can Help Detect Pretraining Data from Large Language Models
by: Zhang, Hengxiang, et al.
Published: (2024)

Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting
by: Wang, Cheng, et al.
Published: (2026)

Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
by: Zhang, Xichen, et al.
Published: (2025)

Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild
by: Zhao, Xinyu, et al.
Published: (2024)

Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements
by: Li, Ming, et al.
Published: (2024)

H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs
by: Tekin, Selim Furkan, et al.
Published: (2024)

UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making
by: Duan, Jinhao, et al.
Published: (2025)

Finding the Cracks: Improving LLMs Reasoning with Paraphrastic Probing and Consistency Verification
by: Shi, Weili, et al.
Published: (2026)

Can LLMs Follow Simple Rules?
by: Mu, Norman, et al.
Published: (2023)

Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation
by: Tang, Pingzhi, et al.
Published: (2026)

Can Post-Training Transform LLMs into Causal Reasoners?
by: Chen, Junqi, et al.
Published: (2026)

Stratified GRPO: Handling Structural Heterogeneity in Reinforcement Learning of LLM Search Agents
by: Zhu, Mingkang, et al.
Published: (2025)

$\textit{Agents Under Siege}$: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks
by: Khan, Rana Muhammad Shahroz, et al.
Published: (2025)

Stabilizing Reasoning in Medical LLMs with Continued Pretraining and Reasoning Preference Optimization
by: Kawakami, Wataru, et al.
Published: (2025)

Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends
by: Yao, Chaorui, et al.
Published: (2025)

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
by: Zhao, Chengshuai, et al.
Published: (2025)

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
by: Ramesh, Shyam Sundhar, et al.
Published: (2026)

Can LLMs Convert Graphs to Text-Attributed Graphs?
by: Wang, Zehong, et al.
Published: (2024)

Climbing the Ladder of Reasoning: What LLMs Can-and Still Can't-Solve after SFT?
by: Sun, Yiyou, et al.
Published: (2025)

Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?
by: Öncel, Fırat, et al.
Published: (2024)

MMR-GRPO: Accelerating GRPO-Style Training through Diversity-Aware Reward Reweighting
by: Wei, Kangda, et al.
Published: (2026)

MiGrATe: Mixed-Policy GRPO for Adaptation at Test-Time
by: Phan, Peter, et al.
Published: (2025)

ixi-GEN: Efficient Industrial sLLMs through Domain Adaptive Continual Pretraining
by: Kim, Seonwu, et al.
Published: (2025)