Cover Image

Learn to Reason Efficiently with Adaptive Length-based Reward Shaping

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Wei, Zhou, Ruochen, Deng, Yiyun, Huang, Yuzhen, Liu, Junteng, Deng, Yuntian, Zhang, Yizhe, He, Junxian
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoning
by: Huang, Yuzhen, et al.
Published: (2025)

SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild
by: Zeng, Weihao, et al.
Published: (2025)

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
by: Zeng, Weihao, et al.
Published: (2024)

Compression Represents Intelligence Linearly
by: Huang, Yuzhen, et al.
Published: (2024)

From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
by: Deng, Yuntian, et al.
Published: (2024)

In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
by: Chen, Shiqi, et al.
Published: (2024)

From Chat Logs to Collective Insights: Aggregative Question Answering
by: Zhang, Wentao, et al.
Published: (2025)

CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
by: Zheng, Congmin, et al.
Published: (2025)

Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search
by: Cui, Yingqian, et al.
Published: (2025)

Interactive Training: Feedback-Driven Neural Network Optimization
by: Zhang, Wentao, et al.
Published: (2025)

TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar
by: Li, Yinxi, et al.
Published: (2025)

Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy
by: Liu, Chris Yuhao, et al.
Published: (2025)

Text2Reward: Reward Shaping with Language Models for Reinforcement Learning
by: Xie, Tianbao, et al.
Published: (2023)

Diving into Self-Evolving Training for Multimodal Reasoning
by: Liu, Wei, et al.
Published: (2024)

What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
by: Liu, Wei, et al.
Published: (2023)

Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations
by: Liu, Wei, et al.
Published: (2026)

On Designing Effective RL Reward at Training Time for LLM Reasoning
by: Gao, Jiaxuan, et al.
Published: (2024)

Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning Exploration
by: Deng, Wenhao, et al.
Published: (2025)

Stable Adaptive Thinking via Advantage Shaping and Length-Aware Gradient Regulation
by: Xu, Zihang, et al.
Published: (2026)

Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning
by: Li, Xintong, et al.
Published: (2026)

Reward Shaping to Mitigate Reward Hacking in RLHF
by: Fu, Jiayi, et al.
Published: (2025)

SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
by: Liu, Junteng, et al.
Published: (2025)

The Lessons of Developing Process Reward Models in Mathematical Reasoning
by: Zhang, Zhenru, et al.
Published: (2025)

AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling
by: Liu, Zihan, et al.
Published: (2024)

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
by: Liu, Yang, et al.
Published: (2026)

Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended Reasoning
by: Ye, Zhiling, et al.
Published: (2025)

ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning
by: Qiao, Ziqing, et al.
Published: (2025)

Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective
by: He, Shenghua, et al.
Published: (2025)

Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model
by: Li, Yanhao, et al.
Published: (2025)

Adaptive Milestone Reward for GUI Agents
by: Zheng, Congmin, et al.
Published: (2026)

Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
by: Ma, Zhengzhao, et al.
Published: (2026)

Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning
by: Ma, Haozhe, et al.
Published: (2024)

Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning
by: Xu, Fangzhi, et al.
Published: (2025)

Weak-to-Strong Elicitation via Mismatched Wrong Drafts
by: Deng, Wei
Published: (2026)

RelayLLM: Efficient Reasoning via Collaborative Decoding
by: Huang, Chengsong, et al.
Published: (2026)

AutoRule: Reasoning Chain-of-thought Extracted Rule-based Rewards Improve Preference Learning
by: Wang, Tevin, et al.
Published: (2025)

SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
by: Huang, Kaixuan, et al.
Published: (2024)

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
by: Gunjal, Anisha, et al.
Published: (2025)

Process Rewards with Learned Reliability
by: Li, Jinyuan, et al.
Published: (2026)

Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
by: Deng, Mingkai, et al.
Published: (2026)