Copertina

Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yao, Xinhao, Ren, Ruifeng, Liao, Yun, Ding, Lizhong, Liu, Yong
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

CoT-Space: A Theoretical Framework for Internal Slow-Thinking via Reinforcement Learning
di: Gan, Zeyu, et al.
Pubblicazione: (2025)

D-SCoRE: Document-Centric Segmentation and CoT Reasoning with Structured Export for QA-CoT Data Generation
di: Zhou, Weibo, et al.
Pubblicazione: (2025)

CoT Referring: Improving Referring Expression Tasks with Grounded Reasoning
di: Dong, Qihua, et al.
Pubblicazione: (2025)

CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process
di: Bi, Jinhe, et al.
Pubblicazione: (2025)

Efficient Long CoT Reasoning in Small Language Models
di: Wang, Zhaoyang, et al.
Pubblicazione: (2025)

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

MedCLM: Learning to Localize and Reason via a CoT-Curriculum in Medical Vision-Language Models
di: Kim, Soo Yong, et al.
Pubblicazione: (2025)

Video-Skill-CoT: Skill-based Chain-of-Thoughts for Domain-Adaptive Video Reasoning
di: Lee, Daeun, et al.
Pubblicazione: (2025)

Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization
di: Luo, Haotian, et al.
Pubblicazione: (2025)

Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning
di: Yang, Cehao, et al.
Pubblicazione: (2025)

KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning
di: Mondal, Debjyoti, et al.
Pubblicazione: (2024)

Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning
di: Li, Jiachun, et al.
Pubblicazione: (2024)

CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models
di: Li, Feiyang, et al.
Pubblicazione: (2025)

Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning
di: Gan, Zeyu, et al.
Pubblicazione: (2025)

Improve Student's Reasoning Generalizability through Cascading Decomposed CoTs Distillation
di: Dai, Chengwei, et al.
Pubblicazione: (2024)

Boosting Process-Correct CoT Reasoning by Modeling Solvability of Multiple-Choice QA
di: Schumann, Raphael, et al.
Pubblicazione: (2025)

The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think
di: Lee, Seongyun, et al.
Pubblicazione: (2025)

CMDAG: A Chinese Metaphor Dataset with Annotated Grounds as CoT for Boosting Metaphor Generation
di: Shao, Yujie, et al.
Pubblicazione: (2024)

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

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

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

SIM-CoT: Supervised Implicit Chain-of-Thought
di: Wei, Xilin, et al.
Pubblicazione: (2025)

TIBSTC-CoT: A Multi-Domain Instruction Dataset for Chain-of-Thought Reasoning in Language Models
di: Gao, Fan, et al.
Pubblicazione: (2025)

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

CoT is Not True Reasoning, It Is Just a Tight Constraint to Imitate: A Theory Perspective
di: Shao, Jintian, et al.
Pubblicazione: (2025)

Rethinking Reasoning in LLMs: Neuro-Symbolic Local RetoMaton Beyond ICL and CoT
di: Mamidala, Rushitha Santhoshi, et al.
Pubblicazione: (2025)

Chain-of-Tools: Utilizing Massive Unseen Tools in the CoT Reasoning of Frozen Language Models
di: Wu, Mengsong, et al.
Pubblicazione: (2025)

Skill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills
di: Chen, Justin Chih-Yao, et al.
Pubblicazione: (2025)

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

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation
di: Kumarage, Tharindu, et al.
Pubblicazione: (2025)

Effectiveness of Zero-shot-CoT in Japanese Prompts
di: Takayama, Shusuke, et al.
Pubblicazione: (2025)

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

KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning
di: Xu, Hongling, et al.
Pubblicazione: (2025)

Context-CoT: Enhancing Context Learning via High-Quality Reasoning Synthesis
di: Jin, Hongbo, et al.
Pubblicazione: (2026)

Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning
di: Lyu, Tianwen, et al.
Pubblicazione: (2025)

What Makes In-context Learning Effective for Mathematical Reasoning: A Theoretical Analysis
di: Liu, Jiayu, et al.
Pubblicazione: (2024)

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

ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks
di: Xiong, Kai, et al.
Pubblicazione: (2022)

Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies
di: Cheng, Sitao, et al.
Pubblicazione: (2025)