The Flow has not summarised this story yet — read it at arXiv AI.
arXiv:2607. 09489v1 Announce Type: new Abstract: An AI system's output is not the fact or world state it appears to describe, but rather an engineered representation.
arXiv:2607. 29405v1 Announce Type: new Abstract: Agentic AI systems act through multi-step trajectories that combine planning, tool use, memory, interaction, and adaptation.
arXiv:2608. 11274v1 Announce Type: cross Abstract: The dominant paradigm treats AI safety as a property to be instilled during model training via RLHF, DPO, or Constitutional AI.
arXiv:2608. 05602v1 Announce Type: new Abstract: Generative AI systems are increasingly deployed in high-stakes professional contexts, where their outputs shape what users believe, how they reason, and what they treat as settled.
arXiv:2609.37457v1 Announce Type: new Abstract: Enterprise artificial-intelligence agents increasingly call tools, modify infrastructure, and process protected data, creating a need to separate actio...
arXiv:2607. 07229v1 Announce Type: new Abstract: Prior work has shown that chain-of-thought (CoT) reasoning is often unfaithful: a model's stated reasoning does not reliably reflect the process that produced its output.