method · first seen 4 Oct 2026
chain-of-thought monitoring
Also: CoT monitoring, CoT monitorability, AI control monitoring, agentic misalignment monitoring, chain-of-thought monitorability
Detecting misbehavior in language models by inspecting their intermediate reasoning traces.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Monitorability Disposition in Large Reasoning ModelsPapers · 4 Oct 2026 · Shahriar Golchin, Marc Wetter
- Reasoning-Token Spikes Under Prompted Untruthful Responses in Large Language ModelsPapers · 7 Oct 2026 · Maverick Morales, Tomáš Dominik, Vermut Gao, Katrina Shirey, Paulius Rimkevi…
- Chain of Thought Monitoring Can Fail Even When CoT Is NecessaryPapers · 13 Oct 2026 · Lennart Bürger, Piotr Komorowski, Moritz Weckbecker, Evgenii Kortukov, Aakriti…
- Screwtape: Adversarial Transcript Editing for Monitor Red-TeamingPapers · 14 Oct 2026 · Gosha Kozhevnikov, Tyler Tracy
- Reasoning Models Can Control Their Chains of Thought When They Tell Themselves ToPapers · 16 Oct 2026 · Uriel Dolev, Idan Schwartz, Yoav Goldberg
- OwlSight: A Panoramic Monitor for Chain-of-Thought ReasoningPapers · 16 Oct 2026 · Lewen Yan, Yanxu Zhu, Jie Zhang, Jing Shao
Latest sources
- Reasoning Models Confabulate to Defend Injected Beliefs About Their Own RequestsPapers · 13 Nov 2026 · Yang Ou
- An Operationalization of Opaque Serial DepthPapers · 12 Nov 2026 · Nathan Sheffield, Alek Westover, Lukas Finnveden, Alexa Pan, Julian Stastny, Rya…
- Transparency Disclosures for Chain-of-Thought MonitorabilityPapers · 10 Nov 2026 · Jacob Davies, Theo Bearman
- Designing Effective Monitor-Based Interventions for Mitigating Reward Hacking During RLPapers · 6 Nov 2026 · Aria Wong, Joshua Engels, Neel Nanda
- Stress Testing Chain-of-Thought Monitoring Against Covert MisalignmentPapers · 5 Nov 2026 · Yao Huang, Yifan Wang, Yitong Sun, Yichi Zhang, Yinpeng Dong
- Chain-of-Thought Oversight Requires Separate Evidence for Faithfulness and MonitorabilityPapers · 1 Nov 2026 · Sichao Li, Sai Ma, Xiyang Hu, Chudi Zhong, Tongliang Liu
- Opening the Box Changes the Cat: LLMs Detect Chain-of-Thought Monitoring - What now?Papers · 29 Oct 2026 · Amir Jalilifard, Marcos Medeiros Raimundo, Anderson Rocha
- The First Few Tokens Matter: Understanding Chain-of-Thought ControllabilityPapers · 29 Oct 2026 · Hugh Van Deventer, Dmitrii Troitskii, Laura Ruis
- Back to Basics: Formal Analysis Hints Improve Weak-to-Strong MonitoringPapers · 25 Oct 2026 · Daniel Ben-Levi, Judah Goldfeder, Mateusz Dziemian, Raja Moreno
- Learning to Be Monitored: Causal Bounds and Intervention-Aware Post-Training Recipes for Chain-of-Thought MonitorabilityPapers · 22 Oct 2026 · Qiang Fu, Xinyue Li, Andre Wibisono, Arman Cohan
- Monitorability Is Trainable: Post-Training for Chain-of-Thought MonitorabilityPapers · 21 Oct 2026 · Usman Anwar, Tim Bakker, Christos Louizos, David Krueger
- Reward Misspecification Degrades Chain-of-Thought MonitorabilityPapers · 20 Oct 2026 · Tianyi Lorena Yan, John Hewitt