001 The Biosecurity Blind Spot: Systematic Dual-use Detection in Open Science Infrastructure arXiv Paper Vasudha Sharma, C. Singh et al. May 10 002 Are we Doomed to an AI Race? Why Self-Interest Could Drive Countries Towards a Moratorium on Superintelligence arXiv Paper Edward Roussel, Lode Lauwaert et al. May 2 003 Code World Model Preparedness Report arXiv Paper D. Song, Peter Ney et al. May 1 004 Exploration Hacking: Can LLMs Learn to Resist RL Training? arXiv Paper Eyon Jang, Damon Falck et al. Apr 30 005 Scheming in the wild: detecting real-world AI scheming incidents with open-source intelligence arXiv Paper Tommy Shaffer Shane, Simon Mylius et al. Apr 10 006 Chain-of-Authorization: Embedding authorization into large language models arXiv Paper Yang Li, Yule Liu et al. Mar 24 007 Consequentialist Objectives and Catastrophe arXiv Paper Henrik Marklund, Alex Infanger et al. Mar 16 008 RCTs for Frontier AI Governance: Methodological Challenges and Solutions for Human Uplift Studies arXiv Paper Patricia Paskov, Kevin Wei et al. Mar 11 009 The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness arXiv Paper Subramanyam Sahoo, Aman Chadha et al. Mar 10 010 Jailbreaking Embodied LLMs via Action-level Manipulation arXiv Paper Xinyu Huang, Qiang Yang et al. Mar 2 011 A Multi-Turn Framework for Evaluating AI Misuse in Fraud and Cybercrime Scenarios arXiv Paper Kimberly T. Mai, Anna Gausen et al. Feb 25 012 Implicit Intelligence -- Evaluating Agents on What Users Don't Say arXiv Paper Ved Sirdeshmukh, Marc Wetter Feb 23 013 Measuring Mid-2025 LLM-Assistance on Novice Performance in Biology arXiv Paper Shenda Hong, Alexander Kleinman et al. Feb 18 014 Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5 arXiv Paper Dongrui Liu, Yi Yu et al. Feb 16 015 Small models, big threats: Characterizing safety challenges from low-compute AI models arXiv Paper Prateek Puri Jan 29 016 VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning arXiv Paper Vikash Singh, Darion Cassel et al. Jan 27 017 AI Regulation Regimes and Competitive Outcomes: A Game-Theoretic Analysis of Regulatory Competition in Frontier Technologies Semantic Scholar Paper S. Paul, Herman Sahni Jan 1 018 AI Systems That Think, Team, and Fight Semantic Scholar Paper Svitlana Volkova Jan 1 019 AI-Driven Navigational Assistance for Visually Impaired Persons Semantic Scholar Paper Venkatesh, Jahnavi Thupalli et al. Jan 1 020 ARTIFICIAL INTELLIGENCE IN HOSPITALITY: TRANSFORMING THE HOTEL INDUSTRY WHILE PRESERVING EMPATHY AND TRADITIONAL HOSPITALITY Semantic Scholar Paper Olaoluwa Fowosere Jan 1 021 Advancing Knotted Protein Design with ESM3: Guided Generation and Topological Insights Semantic Scholar Paper Eva Maršálková, Petr Šimeček Jan 1 022 Artificial Intelligence and the Future of Strategic Stability Semantic Scholar Paper Michael C. Horowitz Jan 1 023 Awareness, Competence, and Perceptions of Augmented Reality, Virtual Reality, and the Metaverse among Pakistani University Librarians Semantic Scholar Paper Hina Sardar, Muhammad Kabir Khan Jan 1 024 Beyond Content Filtering: A “Circuit Breaker” Architecture for Autonomous Agent Action Safety Semantic Scholar Paper H. Sridharan, Reshma Nair Jan 1 025 Designing an AI-Enhanced Web Crawler for Semantic Data Extraction and Knowledge Graph Construction Semantic Scholar Paper Chitiz Tayal Jan 1 026 Emotional Resonance Matching for Personalized E-Commerce Re-Engagement System Using Machine Learning and Generative AI Semantic Scholar Paper S. M Jan 1 027 From Data to Decisions: Harnessing the Potential of Language Based AI in Drilling Semantic Scholar Paper C. Chatar, P. Sheth Jan 1 028 From Emotion to Action: AURORA’s Sentiment-Based Model for Tourism Decisions Semantic Scholar Paper M. Badouch, M. Boutaounte Jan 1 029 Frontier Safety Policies for AI Emergency Preparedness in China Semantic Scholar Paper James Zhang, Miles Kodama et al. Jan 1 030 GenAI-Powered Autonomous Cyber Offense-Defense: An Explainable LLM Red-vs-Blue Simulation and Self-Defense Framework Semantic Scholar Paper Haitian Du Jan 1 031 Multi-Agentic Generative AI Framework for Accelerating Field Development Planning Semantic Scholar Paper S. Ramatullayev, S. Su et al. Jan 1 032 Personalised LLMs and the risks of the digital twin metaphor Semantic Scholar Paper M. Annoni, Davide Battisti et al. Jan 1 033 Probing Adversarial Robustness of Protein Language Models: A Reproducible Case Study of ESM-2 Under Substitution-Based Attacks Semantic Scholar Paper Md. Robiul Islam Niloy, Zafer Aydin et al. Jan 1 034 RitualLab: An AI-in-the-loop Collaborative Platform for Designing and Auditing Well-being-Aware Brand Narratives Semantic Scholar Paper Yong Zhen, Ethan Jing Li et al. Jan 1 035 Sentinel-Math: A Framework for Neural Intent Monitoring and SafetyCircuit-Breaking Against Semantically Disguised Logical Tasks in LLMs Semantic Scholar Paper Jing Zhang, Yaowei Wang et al. Jan 1 036 Six misconceptions about large language models: A minimal model and diagnostic taxonomy Semantic Scholar Paper Zhicheng Lin Jan 1 037 Structural Capability Containment in Advanced AI Systems A Foundational Framework for Multi-Jurisdiction Safety Architectures Semantic Scholar Paper Gaston Rey Jan 1 038 Students’ Experiences Using an AI-Powered Speaking Tool in English Courses in Higher Education [Abstract] Semantic Scholar Paper Ilan Daniels Rahimi, Gila Cohen Zilka et al. Jan 1 039 Technical Note Three: The Horizon Scan From V = 0 – Compositional Opacity And Catastrophic Risk Under Quantum Integration Semantic Scholar Paper Andrew Devin Jan 1 040 Biosecurity-Aware AI: Agentic Risk Auditing of Soft Prompt Attacks on ESM-Based Variant Predictors arXiv Paper Huixin Zhan Dec 19, 2025 041 How frontier AI companies could implement an internal audit function arXiv Paper F. Gómez, A. Buick et al. Dec 16, 2025 042 Safe for Whom? Rethinking How We Evaluate the Safety of LLMs for Real Users arXiv Paper Manon Kempermann, Sai Suresh Macharla Vasu et al. Dec 11, 2025 043 Biothreat Benchmark Generation Framework for Evaluating Frontier AI Models I: The Task-Query Architecture arXiv Paper Gary Ackerman, Brandon Behlendorf et al. Dec 9, 2025 044 Biothreat Benchmark Generation Framework for Evaluating Frontier AI Models II: Benchmark Generation Process arXiv Paper Gary Ackerman, Z. Kallenborn et al. Dec 9, 2025 045 Biothreat Benchmark Generation Framework for Evaluating Frontier AI Models III: Implementing the Bacterial Biothreat Benchmark (B3) Dataset arXiv Paper Gary Ackerman, Theodore Wilson et al. Dec 9, 2025 046 The Role of Risk Modeling in Advanced AI Risk Management arXiv Paper Chlo'e Touzet, H. Papadatos et al. Dec 9, 2025 047 Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs arXiv Paper Igor Shilov, Alex Cloud et al. Dec 5, 2025 048 Evaluating AI Providers' Frontier Safety Frameworks arXiv Paper Lily Stelling, Malcolm Murray et al. Dec 1, 2025 049 PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach arXiv Paper Udari Madhushani Sehwag, Shayan Shabihi et al. Nov 24, 2025 050 Evaluating Adversarial Vulnerabilities in Modern Large Language Models arXiv Paper Tom Perel Nov 21, 2025 051 An International Agreement to Prevent the Premature Creation of Artificial Superintelligence arXiv Paper Aaron Scher, David Abecassis et al. Nov 13, 2025 052 LTD-Bench: Evaluating Large Language Models by Letting Them Draw arXiv Paper Li Lin, Ke Li et al. Nov 4, 2025 053 SciTrust 2.0: A Comprehensive Framework for Evaluating Trustworthiness of Large Language Models in Scientific Applications arXiv Paper Emily Herron, Junqi Yin et al. Oct 29, 2025 054 Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety arXiv Paper V. Bonagiri, P. Kumaraguru et al. Oct 18, 2025 055 PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities arXiv Paper Zicheng Liu, Lige Huang et al. Oct 13, 2025 056 The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives arXiv Paper Matthieu Bou, Nyal Patel et al. Oct 7, 2025 057 How Catastrophic is Your LLM? Certifying Risk in Conversation arXiv Paper Chengxiao Wang, Isha Chaudhary et al. Oct 4, 2025 058 Evaluation Awareness Scales Predictably in Open-Weights Large Language Models arXiv Paper Maheep Chaudhary, Ian Su et al. Sep 10, 2025 059 Constitutional Law and AI Governance: Constraints on Model Licensing and Research Classification arXiv Paper A. Mark, Aaron Scher Sep 3, 2025 060 STREAM (ChemBio): A Standard for Transparently Reporting Evaluations in AI Model Reports arXiv Paper Tegan McCaslin, Jide Alaga et al. Aug 13, 2025