Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings

arXiv:2603.20620v1 Announce Type: new Abstract: Can we trust the reasoning traces that large reasoning models (LRMs) produce? We investigate whether these traces faithfully

arXiv:2607.08066v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is a promising safety mechanism for AI agents, based on the premise that visible reasoning traces

arXiv:2603.25412v1 Announce Type: new Abstract: Large language models (LLMs) increasingly rely on explicit chain-of-thought (CoT) reasoning to solve complex tasks, yet the safety

arXiv:2604.23460v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning has emerged as a key technique for eliciting complex reasoning in Large Language Models (LLMs).

arXiv:2604.15390v1 Announce Type: cross Abstract: Code deobfuscation is the task of recovering a readable version of a program while preserving its original behavior. In practice,

arXiv:2604.23270v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has emerged as a simple and effective way to elicit step-by-step solutions from large language

OpenAI introduces CoT-Control and finds reasoning models struggle to control their chains of thought, reinforcing monitorability as an AI safety safeguard.

arXiv:2609.18346v1 Announce Type: new Abstract: Large language models (LLM) deployed as autonomous pricing agents may sustain supracompetitive prices through tacit coordination.