{"total":56,"rows":[{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64,"area":"lr"},{"id":"2506.19248","title":"Inference-Time Reward Hacking in Large Language Models","created":"2025-06-24","cited_by_count":34,"area":"alignment"},{"id":"2605.02964","title":"Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use","created":"2026-05-03","cited_by_count":31,"area":"agents"},{"id":"2506.23844","title":"A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents","created":"2025-06-30","cited_by_count":29,"area":"agents"},{"id":"2503.16248","title":"Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents","created":"2025-03-20","cited_by_count":24,"area":"safety"},{"id":"2512.16301","title":"Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills","created":"2025-12-18","cited_by_count":22,"area":"agents"},{"id":"2510.06445","title":"A Survey on Agentic Security: Applications, Threats and Defenses","created":"2025-10-07","cited_by_count":20,"area":"agents"},{"id":"2505.14633","title":"Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas","created":"2025-05-20","cited_by_count":18,"area":null},{"id":"2512.01295","title":"Systems Security Foundations for Agentic Computing","created":"2025-12-01","cited_by_count":13,"area":"agents"},{"id":"2604.23338","title":"A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework","created":"2026-04-25","cited_by_count":11,"area":"agents"},{"id":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"id":"2605.20744","title":"Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale","created":"2026-05-20","cited_by_count":10,"area":"alignment"},{"id":"2607.28802","title":"Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures","created":"2026-07-30","cited_by_count":10,"area":null},{"id":"2509.20393","title":"The Secret Agenda: LLMs Strategically Lie and Our Current Safety Tools Are Blind","created":"2025-09-23","cited_by_count":8,"area":null},{"id":"2508.14927","title":"AI Testing Should Account for Sophisticated Strategic Behaviour","created":"2025-08-19","cited_by_count":6,"area":null},{"id":"2607.00038","title":"Stop Hand-Holding Your Coding Agent: Engineering the Loops that Replace Step-by-Step Prompting","created":"2026-06-28","cited_by_count":5,"area":"agents"},{"id":"2609.04170","title":"A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms","created":"2026-09-03","cited_by_count":5,"area":null},{"id":"2604.19459","title":"Do LLMs Game Formalization? Evaluating Faithfulness in Logical Reasoning","created":"2026-04-21","cited_by_count":4,"area":"lr"},{"id":"2606.15385","title":"Reward Hacking in Language Model Agents: Revisiting AI Safety Gridworlds","created":"2026-06-13","cited_by_count":4,"area":"agents"},{"id":"2606.28430","title":"Building to the Test: Coding Agents Deliver What You Check, Not What You Requested","created":"2026-06-26","cited_by_count":4,"area":"agents"},{"id":"2608.30724","title":"BAITBENCH: Measuring Agent Reward Hacking with Optional Shortcuts Planted in ML Tasks","created":"2026-08-31","cited_by_count":4,"area":"agents"},{"id":"2507.02977","title":"LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance","created":"2025-06-30","cited_by_count":3,"area":null},{"id":"2605.00226","title":"Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions","created":"2026-04-30","cited_by_count":3,"area":null},{"id":"2605.02269","title":"Towards Understanding Specification Gaming in Reasoning Models","created":"2026-05-04","cited_by_count":3,"area":"lr"},{"id":"2605.10481","title":"Safe Multi-Agent Behavior Must Be Maintained, Not Merely Asserted: Constraint Drift in LLM-Based Multi-Agent Systems","created":"2026-05-11","cited_by_count":3,"area":"agents"},{"id":"2607.18966","title":"Measuring Reward-Seeking via Contrastive Belief Updates","created":"2026-07-21","cited_by_count":3,"area":"alignment"},{"id":"2607.21763","title":"Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks","created":"2026-07-23","cited_by_count":3,"area":null},{"id":"2509.11398","title":"From Firewalls to Frontiers: AI Red-Teaming is a Domain-Specific Evolution of Cyber Red-Teaming","created":"2025-09-14","cited_by_count":2,"area":null},{"id":"2512.07665","title":"Reliable agent engineering should integrate machine-compatible organizational principles","created":"2025-12-08","cited_by_count":2,"area":"agents"},{"id":"2604.20200","title":"Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows","created":"2026-04-22","cited_by_count":2,"area":"agents"},{"id":"2609.19101","title":"Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations","created":"2026-09-16","cited_by_count":2,"area":"alignment"},{"id":"2505.07846","title":"Winning at All Cost: A Small Environment for Eliciting Specification Gaming Behaviors in Large Language Models","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2505.17106","title":"RRTL: Red Teaming Reasoning Large Language Models in Tool Learning","created":"2025-05-21","cited_by_count":1,"area":"lr"},{"id":"2510.08624","title":"Do LLMs Know They Are Being Tested? Evaluation Awareness and Incentive-Sensitive Failures in GPT-OSS-20B","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2606.26071","title":"Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.18239","title":"SysAdmin: Measuring Instrumental Power-Seeking in Frontier AI","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2609.32390","title":"Reward Hacking and Agent Containment Failure: A Monte Carlo Study Based on the 2026 Hugging Face Incident","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2506.03568","title":"Confidence-Guided Human-AI Collaboration: Reinforcement Learning with Distributional Proxy Value Propagation for Autonomous Driving","created":"2025-06-04","cited_by_count":0,"area":"driving"},{"id":"2510.02840","title":"Take Goodhart Seriously: Principled Limit on General-Purpose AI Optimization","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2511.23092","title":"Does Self-Evaluation Enable Wireheading in Language Models?","created":"2025-11-28","cited_by_count":0,"area":"alignment"},{"id":"2602.04196","title":"The Missing Half: Unveiling Training-time Implicit Safety Risks Beyond Deployment","created":"2026-02-04","cited_by_count":0,"area":"safety"},{"id":"2603.10091","title":"Multi-Stream Perturbation Attack: Breaking Safety Alignment of Thinking LLMs Through Concurrent Task Interference","created":"2026-03-10","cited_by_count":0,"area":"lr"},{"id":"2606.12442","title":"Reframing AI Loss of Control: What Control Is, How to Have It, How to Lose It","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.20615","title":"Specifying AI-SDLC Processes: A Protocol Language for Human-Agent Boundaries","created":"2026-05-24","cited_by_count":0,"area":"agents"},{"id":"2606.28863","title":"Defeat Devices in AI Systems","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2606.30219","title":"EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.01585","title":"Semantic Alignment of AI Models: Concept Collapse, Checkpoint Dynamics, and Cross-Lingual Transfer","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.22103","title":"Hack-Verifiable Terminal Bench: Evaluating Reward Hacking in Terminal Tasks","created":"2026-08-22","cited_by_count":0,"area":"alignment"},{"id":"2609.03189","title":"Reducing Catastrophic Risk from AI with Systematic Monitoring and Evaluation of Rogue AI Progression","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.06649","title":"Inducing Emergent Misalignment from Reward Hacks with Iterative DPO","created":"2026-09-06","cited_by_count":0,"area":"alignment"},{"id":"2609.23894","title":"Connecting the Dots in Agentic AI Security: A Cross-Dimensional Threat Taxonomy, Evaluation Maturity, and Open Challenges","created":"2026-09-20","cited_by_count":0,"area":"agents"},{"id":"2609.36139","title":"Language Models Are \"Insecure\" Reporters","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.04793","title":"Pressure, Context, and Machine Self-Control: A Criminological Test of Reward Hacking in Generative AI Models","created":"2026-10-03","cited_by_count":0,"area":"alignment"},{"id":"2610.05170","title":"Verification Trap: Understanding Test-Time Selection Failures under False Premises in Code Generation","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.10468","title":"A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.18792","title":"SEAR: Self-Evolving Agentic Robotics","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}