Reasoning Models Struggle to Control their Chains of Thought
Fuente:
arXiv
Saved in:
| Main Authors: | Yueh-Han, Chen, McCarthy, Robert, Lee, Bruce W., He, He, Kivlichan, Ian, Baker, Bowen, Carroll, Micah, Korbak, Tomek |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Training Agents to Self-Report Misbehavior
by: Lee, Bruce W., et al.
Published: (2026)
by: Lee, Bruce W., et al.
Published: (2026)
Lessons from Studying Two-Hop Latent Reasoning
by: Balesni, Mikita, et al.
Published: (2024)
by: Balesni, Mikita, et al.
Published: (2024)
The Ends Justify the Thoughts: RL-Induced Motivated Reasoning in LLM CoTs
by: Howe, Nikolaus, et al.
Published: (2025)
by: Howe, Nikolaus, et al.
Published: (2025)
How to evaluate control measures for LLM agents? A trajectory from today to superintelligence
by: Korbak, Tomek, et al.
Published: (2025)
by: Korbak, Tomek, et al.
Published: (2025)
Safety Cases: A Scalable Approach to Frontier AI Safety
by: Hilton, Benjamin, et al.
Published: (2025)
by: Hilton, Benjamin, et al.
Published: (2025)
Towards Understanding Specification Gaming in Reasoning Models
by: Nishimura-Gasparian, Kei, et al.
Published: (2026)
by: Nishimura-Gasparian, Kei, et al.
Published: (2026)
When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors
by: Emmons, Scott, et al.
Published: (2025)
by: Emmons, Scott, et al.
Published: (2025)
Monitoring Monitorability
by: Guan, Melody Y., et al.
Published: (2025)
by: Guan, Melody Y., et al.
Published: (2025)
A sketch of an AI control safety case
by: Korbak, Tomek, et al.
Published: (2025)
by: Korbak, Tomek, et al.
Published: (2025)
Polarity Resonance & Resonant Polarity Control (PR-RPC)
by: McCarthy, Kyran
Published: (2025)
by: McCarthy, Kyran
Published: (2025)
Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
by: Ye, Jiacheng, et al.
Published: (2024)
by: Ye, Jiacheng, et al.
Published: (2024)
Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models
by: Cui, Yingqian, et al.
Published: (2025)
by: Cui, Yingqian, et al.
Published: (2025)
A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration
by: Cui, Yingqian, et al.
Published: (2024)
by: Cui, Yingqian, et al.
Published: (2024)
Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs
by: Jin, Bowen, et al.
Published: (2024)
by: Jin, Bowen, et al.
Published: (2024)
Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning
by: Lin, Honglin, et al.
Published: (2025)
by: Lin, Honglin, et al.
Published: (2025)
Facilitating Long Context Understanding via Supervised Chain-of-Thought Reasoning
by: Lin, Jingyang, et al.
Published: (2025)
by: Lin, Jingyang, et al.
Published: (2025)
Policy Frameworks for Transparent Chain-of-Thought Reasoning in Large Language Models
by: Chen, Yihang, et al.
Published: (2025)
by: Chen, Yihang, et al.
Published: (2025)
Robotic Control via Embodied Chain-of-Thought Reasoning
by: Zawalski, Michał, et al.
Published: (2024)
by: Zawalski, Michał, et al.
Published: (2024)
Enhancing Auto-regressive Chain-of-Thought through Loop-Aligned Reasoning
by: Yu, Qifan, et al.
Published: (2025)
by: Yu, Qifan, et al.
Published: (2025)
Implications of feedback solutions to the $S_8$ tension for the baryon fractions of galaxy groups and clusters
by: Salcido, Jaime, et al.
Published: (2024)
by: Salcido, Jaime, et al.
Published: (2024)
Efficient Reasoning for LLMs through Speculative Chain-of-Thought
by: Wang, Jikai, et al.
Published: (2025)
by: Wang, Jikai, et al.
Published: (2025)
Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs
by: Yuan, Hongyuan, et al.
Published: (2026)
by: Yuan, Hongyuan, et al.
Published: (2026)
All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language
by: Guo, Shiyuan, et al.
Published: (2025)
by: Guo, Shiyuan, et al.
Published: (2025)
GRACE: Discriminator-Guided Chain-of-Thought Reasoning
by: Khalifa, Muhammad, et al.
Published: (2023)
by: Khalifa, Muhammad, et al.
Published: (2023)
Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models
by: Pang, Rock Yuren, et al.
Published: (2025)
by: Pang, Rock Yuren, et al.
Published: (2025)
Efficient Reasoning via Chain of Unconscious Thought
by: Gong, Ruihan, et al.
Published: (2025)
by: Gong, Ruihan, et al.
Published: (2025)
Photomicrofiche: A Conservation and Research Tool.
by: McCarthy, Paul H., et al.
Published: (1987)
by: McCarthy, Paul H., et al.
Published: (1987)
Towards a Generative Approach for Emotion Detection and Reasoning
by: Bhaumik, Ankita, et al.
Published: (2024)
by: Bhaumik, Ankita, et al.
Published: (2024)
Reasoning Beyond Chain-of-Thought: A Latent Computational Mode in Large Language Models
by: He, Zhenghao, et al.
Published: (2026)
by: He, Zhenghao, et al.
Published: (2026)
Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time
by: Li, Huihan, et al.
Published: (2025)
by: Li, Huihan, et al.
Published: (2025)
Communist Multiculturalism
by: McCarthy, Susan
Published: (2023)
by: McCarthy, Susan
Published: (2023)
Bat Records from the Caribbean Lowlands of El Peten, Guatemala
by: McCarthy, T. J.
Published: (1982)
by: McCarthy, T. J.
Published: (1982)
Kierkegaard as Psychologist
by: McCarthy, Vincent
Published: (2019)
by: McCarthy, Vincent
Published: (2019)
NCAA Senior VP of Championships brings wide breadth of experience to role
by: Claudine McCarthy
Published: (2025)
by: Claudine McCarthy
Published: (2025)
Learn how positivity can improve work culture
by: Claudine McCarthy
Published: (2025)
by: Claudine McCarthy
Published: (2025)
Willingness to adapt plays key role in supporting success of changing student population
by: Claudine McCarthy
Published: (2024)
by: Claudine McCarthy
Published: (2024)
Student affairs career led to college presidency
by: Claudine McCarthy
Published: (2024)
by: Claudine McCarthy
Published: (2024)
Manage student‐athlete transfers more effectively by following best practices for compliance
by: Claudine McCarthy
Published: (2024)
by: Claudine McCarthy
Published: (2024)
Successful leadership requires learning to become comfortable with ambiguity
by: Claudine McCarthy
Published: (2025)
by: Claudine McCarthy
Published: (2025)
Promote a healthier work culture to boost morale among staff members
by: Claudine McCarthy
Published: (2024)
by: Claudine McCarthy
Published: (2024)
Similar Items
-
Training Agents to Self-Report Misbehavior
by: Lee, Bruce W., et al.
Published: (2026) -
Lessons from Studying Two-Hop Latent Reasoning
by: Balesni, Mikita, et al.
Published: (2024) -
The Ends Justify the Thoughts: RL-Induced Motivated Reasoning in LLM CoTs
by: Howe, Nikolaus, et al.
Published: (2025) -
How to evaluate control measures for LLM agents? A trajectory from today to superintelligence
by: Korbak, Tomek, et al.
Published: (2025) -
Safety Cases: A Scalable Approach to Frontier AI Safety
by: Hilton, Benjamin, et al.
Published: (2025)