Cover Image

Shorter Thoughts, Same Answers: Difficulty-Scaled Segment-Wise RL for CoT Compression

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tian, Ye, Liu, Aijun
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Ends Justify the Thoughts: RL-Induced Motivated Reasoning in LLM CoTs
by: Howe, Nikolaus, et al.
Published: (2025)

CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring
by: Arnav, Benjamin, et al.
Published: (2025)

Hindsight Hint Distillation: Scaffolded Reasoning for SWE Agents from CoT-free Answers
by: Wang, Shengjie, et al.
Published: (2026)

To CoT or To Loop? A Formal Comparison Between Chain-of-Thought and Looped Transformers
by: Xu, Kevin, et al.
Published: (2025)

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

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
by: Sprague, Zayne, et al.
Published: (2024)

Cross Domain Evaluation of Multimodal Chain-of-Thought Reasoning of different datasets into the Amazon CoT Framework
by: Tiwari, Nitya, et al.
Published: (2025)

CoScale-RL: Efficient Post-Training by Co-Scaling Data and Computation
by: Chen, Yutong, et al.
Published: (2026)

CoT-ICL Lab: A Synthetic Framework for Studying Chain-of-Thought Learning from In-Context Demonstrations
by: Kothapalli, Vignesh, et al.
Published: (2025)

CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
by: Zhao, Qingqing, et al.
Published: (2025)

DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation
by: Zhou, Yang, et al.
Published: (2026)

Exploring the Limitations of Mamba in COPY and CoT Reasoning
by: Ren, Ruifeng, et al.
Published: (2024)

Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning
by: Mahrooghi, Ilia, et al.
Published: (2026)

Data Shifts Hurt CoT: A Theoretical Study
by: Yin, Lang, et al.
Published: (2025)

Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?
by: Qu, Yun, et al.
Published: (2025)

Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO
by: Tong, Chengzhuo, et al.
Published: (2025)

The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation
by: Zhang, Ruichen, et al.
Published: (2025)

Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin
by: Queipo-de-Llano, Enrique, et al.
Published: (2025)

Skill Reuse as Compression in Agentic RL
by: Xu, Zhikun, et al.
Published: (2026)

Activation Steering for Chain-of-Thought Compression
by: Azizi, Seyedarmin, et al.
Published: (2025)

RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?
by: Xu, Haotian, et al.
Published: (2025)

Atoms of Thought: Universal EEG Representation Learning with Microstates
by: Tian, Xinyang, et al.
Published: (2026)

PRIMEDrive-CoT: A Precognitive Chain-of-Thought Framework for Uncertainty-Aware Object Interaction in Driving Scene Scenario
by: Mandalika, Sriram, et al.
Published: (2025)

VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal RL
by: Hu, Zengjie, et al.
Published: (2025)

Is continuous CoT better suited for multi-lingual reasoning?
by: Bashir, Ali Hamza, et al.
Published: (2026)

Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
by: Guo, Yiran, et al.
Published: (2025)

Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning
by: Parekh, Swapnil
Published: (2026)

The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
by: Lan, Yifan, et al.
Published: (2026)

CoT-Valve: Length-Compressible Chain-of-Thought Tuning
by: Ma, Xinyin, et al.
Published: (2025)

Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
by: Kim, Juno, et al.
Published: (2025)

How Likely Do LLMs with CoT Mimic Human Reasoning?
by: Bao, Guangsheng, et al.
Published: (2024)

FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation
by: Liu, Xiang, et al.
Published: (2023)

Do Latent-CoT Models Think Step-by-Step? A Mechanistic Study on Sequential Reasoning Tasks
by: Liang, Jia, et al.
Published: (2026)

PepThink-R1: LLM for Interpretable Cyclic Peptide Optimization with CoT SFT and Reinforcement Learning
by: Wang, Ruheng, et al.
Published: (2025)

LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning
by: Ye, Xinwu, et al.
Published: (2026)

Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations
by: Cai, Wenrui, et al.
Published: (2025)

Beyond the Answer: Decoding the Behavior of LLMs as Scientific Reasoners
by: Pandey, Rohan, et al.
Published: (2026)

ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
by: Zhang, Qiang, et al.
Published: (2026)

Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR
by: Bounhar, Abdelaziz, et al.
Published: (2025)

To Think or Not to Think: The Hidden Cost of Meta-Training with Excessive CoT Examples
by: Kothapalli, Vignesh, et al.
Published: (2025)