Cover Image

S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dai, Muzhi, Yang, Chenxu, Si, Qingyi
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

Stable Reinforcement Learning for Efficient Reasoning
by: Dai, Muzhi, et al.
Published: (2025)

Dynamic Early Exit in Reasoning Models
by: Yang, Chenxu, et al.
Published: (2025)

SpecExit: Accelerating Large Reasoning Model via Speculative Exit
by: Yang, Rubing, et al.
Published: (2025)

TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
by: Nagle, Alliot, et al.
Published: (2026)

Beyond Greedy Exits: Improved Early Exit Decisions for Risk Control and Reliability
by: Bajpai, Divya Jyoti, et al.
Published: (2025)

Federated Learning for Collaborative Inference Systems: The Case of Early Exit Networks
by: Kaplan, Caelin, et al.
Published: (2024)

E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
by: Zhang, Shengjun, et al.
Published: (2026)

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

Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning
by: Chen, Benteng, et al.
Published: (2026)

Towards Robust Deep Reinforcement Learning against Environmental State Perturbation
by: Wang, Chenxu, et al.
Published: (2025)

Improving Group Fairness in Knowledge Distillation via Laplace Approximation of Early Exits
by: Fasth, Edvin, et al.
Published: (2025)

AEBNAS: Strengthening Exit Branches in Early-Exit Networks through Hardware-Aware Neural Architecture Search
by: Robben, Oscar, et al.
Published: (2025)

Early-Exit Neural Networks with Nested Prediction Sets
by: Jazbec, Metod, et al.
Published: (2023)

Uncalibrated Reasoning: GRPO Induces Overconfidence for Stochastic Outcomes
by: Bereket, Michael, et al.
Published: (2025)

GRPO-$λ$: Credit Assignment improves LLM Reasoning
by: Parthasarathi, Prasanna, et al.
Published: (2025)

GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning
by: Chen, Yi, et al.
Published: (2025)

Quantifying and Understanding Uncertainty in Large Reasoning Models
by: Li, Yangyi, et al.
Published: (2026)

LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning
by: Akgül, Ömer Faruk, et al.
Published: (2025)

Deep Reinforcement Learning with Task-Adaptive Retrieval via Hypernetwork
by: Jin, Yonggang, et al.
Published: (2023)

Attention Consistency Regularization for Interpretable Early-Exit Neural Networks
by: Zhao, Yanhua
Published: (2026)

SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization
by: Zheng, Zhi, et al.
Published: (2025)

Hetero-SplitEE: Split Learning of Neural Networks with Early Exits for Heterogeneous IoT Devices
by: Oda, Yuki, et al.
Published: (2025)

TableGPT-R1: Advancing Tabular Reasoning Through Reinforcement Learning
by: Yang, Saisai, et al.
Published: (2025)

Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exits
by: Elboher, Yizhak Yisrael, et al.
Published: (2025)

AMIR-GRPO: Inducing Implicit Preference Signals into GRPO
by: Yari, Amir Hossein, et al.
Published: (2026)

DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models
by: Monsefi, Amin Karimi, et al.
Published: (2026)

MC-GRPO: Median-Centered Group Relative Policy Optimization for Small-Rollout Reinforcement Learning
by: Kim, Youngeun
Published: (2026)

On-Sensor Convolutional Neural Networks with Early-Exits
by: Shalby, Hazem Hesham Yousef, et al.
Published: (2025)

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

Know What You Don't Know: Selective Prediction for Early Exit DNNs
by: Bajpai, Divya Jyoti, et al.
Published: (2025)

Comparative Analysis and Parametric Tuning of PPO, GRPO, and DAPO for LLM Reasoning Enhancement
by: Lian, Yongsheng
Published: (2025)

GRPO is Secretly a Process Reward Model
by: Sullivan, Michael, et al.
Published: (2025)

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

Temporal Decisions: Leveraging Temporal Correlation for Efficient Decisions in Early Exit Neural Networks
by: Sponner, Max, et al.
Published: (2024)

Curriculum Learning for Efficient Chain-of-Thought Distillation via Structure-Aware Masking and GRPO
by: Yu, Bowen, et al.
Published: (2026)

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
by: Ren, Yiming, et al.
Published: (2026)

From Reasoning to Code: GRPO Optimization for Underrepresented Languages
by: Pennino, Federico, et al.
Published: (2025)

Mitigating Overthinking in Large Reasoning Models via Difficulty-aware Reinforcement Learning
by: Wan, Qian, et al.
Published: (2026)

Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models
by: Yang, Chenxu, et al.
Published: (2025)

Multi-Path Collaborative Reasoning via Reinforcement Learning
by: Lv, Jindi, et al.
Published: (2025)