Image de couverture de livre

C$^2$GSPG: Confidence-calibrated Group Sequence Policy Gradient towards Self-aware Reasoning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Haotian, Wang, Shuo, Xu, Hongteng
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Confidence-aware Self-Semantic Distillation on Knowledge Graph Embedding
par: Liu, Yichen, et autres
Publié: (2022)

Group Sequence Policy Optimization
par: Zheng, Chujie, et autres
Publié: (2025)

Interpreting and Controlling LLM Reasoning through Integrated Policy Gradient
par: Li, Changming, et autres
Publié: (2026)

SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales
par: Xu, Tianyang, et autres
Publié: (2024)

On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning
par: Zhang, Yifan, et autres
Publié: (2025)

Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization
par: Su, Zhenpeng, et autres
Publié: (2025)

Simple Policy Gradients for Reasoning with Diffusion Language Models
par: Zhan, Anthony
Publié: (2025)

GTPO: Stabilizing Group Relative Policy Optimization via Gradient and Entropy Control
par: Simoni, Marco, et autres
Publié: (2025)

Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization
par: Ding, Yifeng, et autres
Publié: (2025)

AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence
par: Liu, Yuliang, et autres
Publié: (2025)

Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space
par: Li, Hengli, et autres
Publié: (2025)

Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
par: Zhang, Xichen, et autres
Publié: (2025)

MHPO: Modulated Hazard-aware Policy Optimization for Stable Reinforcement Learning
par: Wang, Hongjun, et autres
Publié: (2026)

ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning
par: Qiao, Ziqing, et autres
Publié: (2025)

Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification
par: Liu, Chengwu, et autres
Publié: (2025)

LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning
par: Akgül, Ömer Faruk, et autres
Publié: (2025)

Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMs
par: Bhattacharyya, Sree, et autres
Publié: (2026)

RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling
par: Liu, Yang, et autres
Publié: (2025)

Early Stopping for Large Reasoning Models via Confidence Dynamics
par: Hosseini, Parsa, et autres
Publié: (2026)

CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models
par: Li, Shuozhe, et autres
Publié: (2026)

Steering Large Reasoning Models towards Concise Reasoning via Flow Matching
par: Li, Yawei, et autres
Publié: (2026)

GPG: Generalized Policy Gradient Theorem for Transformer-based Policies
par: Mao, Hangyu, et autres
Publié: (2025)

Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
par: Ma, Zhengzhao, et autres
Publié: (2026)

Advancing General-Purpose Reasoning Models with Modular Gradient Surgery
par: Cai, Min, et autres
Publié: (2026)

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization
par: Yoon, Hee Suk, et autres
Publié: (2025)

SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration
par: Wen, Zhuofan, et autres
Publié: (2026)

Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models
par: Li, Chengao, et autres
Publié: (2025)

Learning to Reason under Off-Policy Guidance
par: Yan, Jianhao, et autres
Publié: (2025)

Group Reasoning Emission Estimation Networks
par: Guo, Yanming, et autres
Publié: (2025)

Grouped Sequency-arranged Rotation: Optimizing Rotation Transformation for Quantization for Free
par: Choi, Euntae, et autres
Publié: (2025)

Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment
par: Wang, Jialu, et autres
Publié: (2026)

SSR: Socratic Self-Refine for Large Language Model Reasoning
par: Shi, Haizhou, et autres
Publié: (2025)

Self-Evaluating LLMs for Multi-Step Tasks: Stepwise Confidence Estimation for Failure Detection
par: Mavi, Vaibhav, et autres
Publié: (2025)

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
par: Liu, Shih-Yang, et autres
Publié: (2026)

Dual-Uncertainty Guided Policy Learning for Multimodal Reasoning
par: Liu, Rui, et autres
Publié: (2025)

Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods
par: Zekri, Oussama, et autres
Publié: (2025)

Optimizing Anytime Reasoning via Budget Relative Policy Optimization
par: Qi, Penghui, et autres
Publié: (2025)

Self-Verification Dilemma: Experience-Driven Suppression of Overused Checking in LLM Reasoning
par: Long, Quanyu, et autres
Publié: (2026)

Leveraging Group Relative Policy Optimization to Advance Large Language Models in Traditional Chinese Medicine
par: Xie, Jiacheng, et autres
Publié: (2025)

Absolute Zero: Reinforced Self-play Reasoning with Zero Data
par: Zhao, Andrew, et autres
Publié: (2025)