# International AI Safety Report 2026

arXiv: https://arxiv.org/abs/2602.21012 · HTML: https://mlsanity.com/paper/2602.21012/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Feb 2026.

## Built on by (most cited first, 22 of 22)

- [Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems](https://mlsanity.com/paper/2604.14228/) (2026)
- [MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models](https://mlsanity.com/paper/2603.28590/) (2026)
- [Tracing Persona Vectors Through LLM Pretraining](https://mlsanity.com/paper/2605.13329/) (2026)
- [DeonticBench: A Benchmark for Reasoning over Rules](https://mlsanity.com/paper/2604.04443/) (2026)
- [Language models recognize dropout and Gaussian noise applied to their activations](https://mlsanity.com/paper/2604.17465/) (2026)
- [Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics](https://mlsanity.com/paper/2605.18549/) (2026)
- [A Formal Security Framework for MCP-Based AI Agents: Threat Taxonomy, Verification Models, and Defense Mechanisms](https://mlsanity.com/paper/2604.05969/) (2026)
- [Agent Behavioral Contracts II: Certifying Compositional Reliability Without Assuming Independence](https://mlsanity.com/paper/2608.12895/) (2026)
- [What if automating AI R&D triggers an intelligence explosion?](https://mlsanity.com/paper/2609.36054/) (2026)
- [RCTs for Frontier AI Governance: Methodological Challenges and Solutions for Human Uplift Studies](https://mlsanity.com/paper/2603.11001/) (2026)
- [Risk Reporting for Developers' Internal AI Model Use](https://mlsanity.com/paper/2604.24966/) (2026)
- [CoT-Guard: Small Models for Strong Monitoring](https://mlsanity.com/paper/2605.12746/) (2026)
- [Securing Multi-Tool AI Agent Chains With Dynamic, Real-Time Compositional Policies](https://mlsanity.com/paper/2607.03423/) (2026)
- [Alignment Plausibility: A New Standard for Assuring AI in Healthcare](https://mlsanity.com/paper/2607.07766/) (2026)
- [The Boundaries of Automation: A Theory of Persistent Human Participation](https://mlsanity.com/paper/2607.21547/) (2026)
- [Privacy-Preserving AI Verification via Minimal Information Disclosure](https://mlsanity.com/paper/2608.02774/) (2026)
- [SVI-DAG: A Structured Variational Inference Approach to Bayesian Causal Discovery](https://mlsanity.com/paper/2608.04930/) (2026)
- [One Perturbation Is Not Enough: Identifiability and Blind Baselines for Behavioral AI Evaluation](https://mlsanity.com/paper/2609.06190/) (2026)
- [Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuning](https://mlsanity.com/paper/2609.09553/) (2026)
- [AI Exposure and AI Resilience: A Two-Dimensional Assessment Framework for Software and Software-Based Business Model](https://mlsanity.com/paper/2609.11321/) (2026)
- [Is this machine playing?](https://mlsanity.com/paper/2610.07130/) (2026)
- [Can Power Draw Constrain Covert Compute? Limits of Analogue Verification for AI Governance](https://mlsanity.com/paper/2610.07476/) (2026)

## Abstract (arXiv)

The International AI Safety Report 2026 synthesises the current scientific evidence on the capabilities, emerging risks, and safety of general-purpose AI systems. The report series was mandated by the nations attending the AI Safety Summit in Bletchley, UK. 29 nations, the UN, the OECD, and the EU each nominated a representative to the report's Expert Advisory Panel. Over 100 AI experts contributed, representing diverse perspectives and disciplines. Led by the Report's Chair, these independent experts collectively had full discretion over the report's content.