Data to 14 Oct 2026

International AI Safety Report

arXiv 2501.17805 ↗First posted 29 Jan 2025cs.CY cs.AI cs.LGcited by 67

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

The first International AI Safety Report comprehensively synthesizes the current evidence on the capabilities, risks, and safety of advanced AI systems. The report was mandated by the nations attending the AI Safety Summit in Bletchley, UK. Thirty nations, the UN, the OECD, and the EU each nominated a representative to the report's Expert Advisory Panel. A total of 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.

Key facts. Cited by 67 papers in the map (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. First posted on arXiv 29 Jan 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 44; 2026: 23.

67 papers.

Sort:

By area:

2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
2025Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometrycited by 61
2025PolyGuard: A Multilingual Safety Moderation Tool for 17 Languagescited by 59
2026The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systemscited by 30
2025Mitigating Deceptive Alignment via Self-Monitoringcited by 29
2025LLM Agents Should Employ Security Principlescited by 29
2025Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agentscited by 27
2026Large Language Model Reasoning Failurescited by 21
2025Risk Analysis Techniques for Governed LLM-based Multi-Agent Systemscited by 18
2025An alignment safety case sketch based on debatecited by 16
2025It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topicscited by 14
2025Do LLMs trust AI regulation? Emerging behaviour of game-theoretic LLM agentscited by 11

38 more

2025AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Securitycited by 10
2025The Singapore Consensus on Global AI Safety Research Prioritiescited by 10
2025OpenFake: An Open Dataset and Platform Toward Real-World Deepfake Detectioncited by 10
2025A Framework to Assess the Persuasion Risks Large Language Model Chatbots Pose to Democratic Societiescited by 9
2025SAGE-Eval: Evaluating LLMs for Systematic Generalizations of Safety Factscited by 8
2025TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Lawcited by 8
2025Practical challenges of control monitoring in frontier AI deploymentscited by 8
2025EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Modelscited by 7
2026How Inference Compute Shapes Frontier LLM Evaluationcited by 7
2025A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.icited by 6
2026Detecting Misbehaviors of Large Vision-Language Models by Evidential Uncertainty Quantificationcited by 6
2025Strong but Brittle: Simple Attacks Subvert Reasoning-based Safety Guardrailscited by 5
2025Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?cited by 4
2025Emergence of psychopathological computations in large language modelscited by 4
2025Unlearning Comparator: A Visual Analytics System for Comparative Evaluation of Machine Unlearning Methodscited by 4
2025Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluationscited by 4
2026From AGI to ASIcited by 4
2025Fair Foundation Models for Medical Image Analysis: Challenges and Perspectivescited by 3
2025The Backfiring Effect of Weak AI Safety Regulationcited by 3
2025Can Media Act as a Soft Regulator of Safe AI Development? A Game Theoretical Analysiscited by 3
2025On the Regulatory Potential of User Interfaces for AI Agent Governancecited by 3
2026PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decodingcited by 3
2025Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.iicited by 2
2025PRISON: Unmasking the Criminal Potential of Large Language Modelscited by 2
2025Jinx: Unlimited LLMs for Probing Alignment Failurescited by 2
2025Linear probes rely on textual evidence: Results from leakage mitigation studies in language modelscited by 2
2025Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanationscited by 2
2025Floating-Point Neural Network Verification at the Software Levelcited by 2
2026Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Modelscited by 2
2026Visuospatial Perspective Taking in Multimodal Language Modelscited by 2
2025Tracr-Injection: Distilling Algorithms into Pre-trained Language Modelscited by 1
2025Integrating Neurosymbolic AI in Advanced Air Mobility: A Comprehensive Surveycited by 1
2025LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systemscited by 1
2026Safer Policy Compliance with Dynamic Epistemic Fallbackcited by 1
2026Designing to Forget: Deep Semi-parametric Models for Unlearningcited by 1
2026I must delete the evidence: AI Agents Explicitly Cover up Fraud and Violent Crimecited by 1
2026Do LLMs have core beliefs?cited by 1
2026The Age of AI Agents Demands A New Scientific Paradigm To Sustain Trustworthy Sciencecited by 1

50 most cited of 67 All 67 (JSON)

Similar, not cited

Close in wording, no citation either way