Image de couverture de livre

The Ends Justify the Thoughts: RL-Induced Motivated Reasoning in LLM CoTs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Howe, Nikolaus, Carroll, Micah
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Shorter Thoughts, Same Answers: Difficulty-Scaled Segment-Wise RL for CoT Compression
par: Tian, Ye, et autres
Publié: (2026)

Cross Domain Evaluation of Multimodal Chain-of-Thought Reasoning of different datasets into the Amazon CoT Framework
par: Tiwari, Nitya, et autres
Publié: (2025)

CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring
par: Arnav, Benjamin, et autres
Publié: (2025)

To CoT or To Loop? A Formal Comparison Between Chain-of-Thought and Looped Transformers
par: Xu, Kevin, et autres
Publié: (2025)

CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
par: Zhao, Qingqing, et autres
Publié: (2025)

From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
par: Deng, Yuntian, et autres
Publié: (2024)

Exploring the Limitations of Mamba in COPY and CoT Reasoning
par: Ren, Ruifeng, et autres
Publié: (2024)

The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation
par: Zhang, Ruichen, et autres
Publié: (2025)

RL + Transformer = A General-Purpose Problem Solver
par: Rentschler, Micah, et autres
Publié: (2025)

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

Token-Efficient RL for LLM Reasoning
par: Lee, Alan, et autres
Publié: (2025)

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
par: Sprague, Zayne, et autres
Publié: (2024)

The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
par: Lan, Yifan, et autres
Publié: (2026)

Hindsight Hint Distillation: Scaffolded Reasoning for SWE Agents from CoT-free Answers
par: Wang, Shengjie, et autres
Publié: (2026)

How Likely Do LLMs with CoT Mimic Human Reasoning?
par: Bao, Guangsheng, et autres
Publié: (2024)

Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
par: Kim, Juno, et autres
Publié: (2025)

Ulterior Motives: Detecting Misaligned Reasoning in Continuous Thought Models
par: Ramjee, Sharan
Publié: (2026)

CoT-ICL Lab: A Synthetic Framework for Studying Chain-of-Thought Learning from In-Context Demonstrations
par: Kothapalli, Vignesh, et autres
Publié: (2025)

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

Accelerating RL for LLM Reasoning with Optimal Advantage Regression
par: Brantley, Kianté, et autres
Publié: (2025)

PepThink-R1: LLM for Interpretable Cyclic Peptide Optimization with CoT SFT and Reinforcement Learning
par: Wang, Ruheng, et autres
Publié: (2025)

Data Shifts Hurt CoT: A Theoretical Study
par: Yin, Lang, et autres
Publié: (2025)

LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning
par: Motwani, Sumeet Ramesh, et autres
Publié: (2026)

rePIRL: Learn PRM with Inverse RL for LLM Reasoning
par: Wu, Xian, et autres
Publié: (2026)

Diversity Progress for Goal Selection in Discriminability-Motivated RL
par: Lintunen, Erik M., et autres
Publié: (2024)

Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning
par: Saparkhan, Raman, et autres
Publié: (2026)

Misalignment from Treating Means as Ends
par: Marklund, Henrik, et autres
Publié: (2025)

CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction
par: Park, Jueon, et autres
Publié: (2025)

Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO
par: Tong, Chengzhuo, et autres
Publié: (2025)

AI Alignment with Changing and Influenceable Reward Functions
par: Carroll, Micah, et autres
Publié: (2024)

LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning
par: Ye, Xinwu, et autres
Publié: (2026)

RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?
par: Xu, Haotian, et autres
Publié: (2025)

Reward Design for Justifiable Sequential Decision-Making
par: Sukovic, Aleksa, et autres
Publié: (2024)

Improve Student's Reasoning Generalizability through Cascading Decomposed CoTs Distillation
par: Dai, Chengwei, et autres
Publié: (2024)

Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL
par: Yao, Jiarui, et autres
Publié: (2025)

Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts
par: Ahmed, Ammar, et autres
Publié: (2025)

Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning
par: Yao, Xinhao, et autres
Publié: (2025)

CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning
par: Chen, Shuxu, et autres
Publié: (2026)

PRIMEDrive-CoT: A Precognitive Chain-of-Thought Framework for Uncertainty-Aware Object Interaction in Driving Scene Scenario
par: Mandalika, Sriram, et autres
Publié: (2025)

ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates
par: Yang, Ling, et autres
Publié: (2025)