Cover Image

Long Is More Important Than Difficult for Training Reasoning Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shen, Si, Huang, Fei, Zhao, Zhixiao, Liu, Chang, Zheng, Tiansheng, Zhu, Danhao
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RevOrder: A Novel Method for Enhanced Arithmetic in Language Models
by: Shen, Si, et al.
Published: (2024)

Attention Reveals More Than Tokens: Training-Free Long-Context Reasoning with Attention-guided Retrieval
by: Zhang, Yuwei, et al.
Published: (2025)

MoreHopQA: More Than Multi-hop Reasoning
by: Schnitzler, Julian, et al.
Published: (2024)

Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Steps
by: Yu, Yijiong, et al.
Published: (2024)

Training With "Paraphrasing the Original Text" Teaches LLM to Better Retrieve in Long-context Tasks
by: Yu, Yijiong, et al.
Published: (2023)

Confidence Should Be Calibrated More Than One Turn Deep
by: Zhang, Zhaohan, et al.
Published: (2026)

More Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models
by: Song, Xurui, et al.
Published: (2025)

More Than Catastrophic Forgetting: Integrating General Capabilities For Domain-Specific LLMs
by: Liu, Chengyuan, et al.
Published: (2024)

Can reasoning models comprehend mathematical problems in Chinese ancient texts? An empirical study based on data from Suanjing Shishu
by: Liu, Chang, et al.
Published: (2025)

Fusing Bidirectional Chains of Thought and Reward Mechanisms A Method for Enhancing Question-Answering Capabilities of Large Language Models for Chinese Intangible Cultural Heritage
by: Liu, Ruilin, et al.
Published: (2025)

CoDAR: Continuous Diffusion Language Models are More Powerful Than You Think
by: Shen, Junzhe, et al.
Published: (2026)

Training-Free Long-Context Scaling of Large Language Models
by: An, Chenxin, et al.
Published: (2024)

QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management
by: Shen, Weizhou, et al.
Published: (2025)

When Models Know More Than They Say: Probing Analogical Reasoning in LLMs
by: McGovern, Hope, et al.
Published: (2026)

PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models
by: Hu, Sihao, et al.
Published: (2024)

Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
by: Huang, Tiansheng, et al.
Published: (2024)

FinLFQA: Evaluating Attributed Text Generation of LLMs in Financial Long-Form Question Answering
by: Long, Yitao, et al.
Published: (2025)

From Context Shift to Stylistic Collapse: Why Training Objectives Matter More Than Scale
by: Mahapatra, Rohan
Published: (2026)

Question Translation Training for Better Multilingual Reasoning
by: Zhu, Wenhao, et al.
Published: (2024)

QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
by: Wan, Fanqi, et al.
Published: (2025)

Hidden in the Haystack: Smaller Needles are More Difficult for LLMs to Find
by: Bianchi, Owen, et al.
Published: (2025)

Trivial Vocabulary Bans Improve LLM Reasoning More Than Deep Linguistic Constraints
by: Jehu-Appiah, Rodney
Published: (2026)

Self-Improving Multilingual Long Reasoning via Translation-Reasoning Integrated Training
by: Liu, Junxiao, et al.
Published: (2026)

Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More
by: Wen, Zichen, et al.
Published: (2025)

LLM-Metrics: Measuring Research Impact Through Large Language Model Memory
by: Shen, Si, et al.
Published: (2026)

Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasons
by: Zhou, Shijia, et al.
Published: (2024)

Are Any-to-Any Models More Consistent Across Modality Transfers Than Specialists?
by: Chung, Jiwan, et al.
Published: (2025)

Mitigating Think-Answer Mismatch in LLM Reasoning Through Noise-Aware Advantage Reweighting
by: Shen, Si, et al.
Published: (2025)

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect
by: Men, Xin, et al.
Published: (2024)

Text or Image? What is More Important in Cross-Domain Generalization Capabilities of Hate Meme Detection Models?
by: Aggarwal, Piush, et al.
Published: (2024)

Should LLM Safety Be More Than Refusing Harmful Instructions?
by: Maskey, Utsav, et al.
Published: (2025)

R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search
by: Wang, Yibo, et al.
Published: (2025)

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs
by: Chen, Jierun, et al.
Published: (2025)

The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights
by: Zhu, Wenhao, et al.
Published: (2024)

LIMO: Less is More for Reasoning
by: Ye, Yixin, et al.
Published: (2025)

T3DM: Test-Time Training-Guided Distribution Shift Modelling for Temporal Knowledge Graph Reasoning
by: Si, Yuehang, et al.
Published: (2025)

Joint Enhancement of Relational Reasoning for Long-Context LLMs
by: Chen, Zhirui, et al.
Published: (2025)

Generating Difficult-to-Translate Texts
by: Zouhar, Vilém, et al.
Published: (2025)

More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning
by: Zhao, Yike, et al.
Published: (2025)

Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning
by: Yu, Qinan, et al.
Published: (2026)