Cover Image

Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Shuyang, Liao, Yusheng, Zhang, Ya, Wang, Yanfeng, Wang, Yu
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Miner:Mining Intrinsic Mastery for Data-Efficient RL in Large Reasoning Models
by: Jiang, Shuyang, et al.
Published: (2026)

TAIA: Large Language Models are Out-of-Distribution Data Learners
by: Jiang, Shuyang, et al.
Published: (2024)

MedCare: Advancing Medical LLMs through Decoupling Clinical Alignment and Knowledge Aggregation
by: Liao, Yusheng, et al.
Published: (2024)

DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction
by: Li, Yiqi, et al.
Published: (2025)

ReflecTool: Towards Reflection-Aware Tool-Augmented Clinical Agents
by: Liao, Yusheng, et al.
Published: (2024)

MING-MOE: Enhancing Medical Multi-Task Learning in Large Language Models with Sparse Mixture of Low-Rank Adapter Experts
by: Liao, Yusheng, et al.
Published: (2024)

MedS$^3$: Towards Medical Slow Thinking with Self-Evolved Soft Dual-sided Process Supervision
by: Jiang, Shuyang, et al.
Published: (2025)

Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking
by: Han, Jinyi, et al.
Published: (2025)

Mitigating Overthinking through Reasoning Shaping
by: Song, Feifan, et al.
Published: (2025)

DecoupleSearch: Decouple Planning and Search via Hierarchical Reward Modeling
by: Sun, Hao, et al.
Published: (2025)

Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future
by: Wang, Yidong, et al.
Published: (2025)

Precedent-Informed Reasoning: Mitigating Overthinking in Large Reasoning Models via Test-Time Precedent Learning
by: Wang, Qianyue, et al.
Published: (2026)

DARC: Decoupled Asymmetric Reasoning Curriculum for LLM Evolution
by: Fan, Shengda, et al.
Published: (2026)

Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring
by: Guan, Weixin, et al.
Published: (2026)

ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention
by: Wang, Xinyan, et al.
Published: (2026)

Let LRMs Break Free from Overthinking via Self-Braking Tuning
by: Zhao, Haoran, et al.
Published: (2025)

The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis
by: Wei, Zihao, et al.
Published: (2025)

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
by: Hassid, Michael, et al.
Published: (2025)

Reasoning or Overthinking: Evaluating Large Language Models on Financial Sentiment Analysis
by: Vamvourellis, Dimitris, et al.
Published: (2025)

Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs
by: Su, Jinyan, et al.
Published: (2025)

Prototypical Reward Network for Data-Efficient RLHF
by: Zhang, Jinghan, et al.
Published: (2024)

Mitigating Overthinking in Large Reasoning Models via Manifold Steering
by: Huang, Yao, et al.
Published: (2025)

Preference Curriculum: LLMs Should Always Be Pretrained on Their Preferred Data
by: Zhang, Xuemiao, et al.
Published: (2025)

RLMR: Reinforcement Learning with Mixed Rewards for Creative Writing
by: Liao, Jianxing, et al.
Published: (2025)

Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation
by: Bin, Yi, et al.
Published: (2025)

Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications
by: Chen, Zhe, et al.
Published: (2025)

Avoiding Overthinking and Underthinking: Curriculum-Aware Budget Scheduling for LLMs
by: Rahman, Amirul, et al.
Published: (2026)

Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis
by: Yadav, Anushka, et al.
Published: (2025)

Leveraging Diverse Modeling Contexts with Collaborating Learning for Neural Machine Translation
by: Liao, Yusheng, et al.
Published: (2024)

Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?
by: Zhang, Yudi, et al.
Published: (2025)

Overthinking the Truth: Understanding how Language Models Process False Demonstrations
by: Halawi, Danny, et al.
Published: (2023)

Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards
by: Li, Ming, et al.
Published: (2025)

SubTokenTest: A Practical Benchmark for Real-World Sub-token Understanding
by: Hou, Shuyang, et al.
Published: (2026)

RewardAnything: Generalizable Principle-Following Reward Models
by: Yu, Zhuohao, et al.
Published: (2025)

Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?
by: Fan, Chenrui, et al.
Published: (2025)

F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
by: Zhang, Ziyin, et al.
Published: (2025)

MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models
by: Tang, Zecheng, et al.
Published: (2026)

Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?
by: Jedidi, Nour, et al.
Published: (2025)

Decoupling Understanding from Reasoning via Problem Space Mapping for Small-Scale Model Reasoning
by: Wang, Li, et al.
Published: (2025)

Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences
by: Karlekar, Sweta, et al.
Published: (2026)