{"total":69,"rows":[{"id":"2506.13651","title":"xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations","created":"2025-06-16","cited_by_count":120,"area":null},{"id":"2507.09089","title":"Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity","created":"2025-07-12","cited_by_count":101,"area":null},{"id":"2512.00193","title":"A Rosetta Stone for AI Benchmarks","created":"2025-11-28","cited_by_count":36,"area":null},{"id":"2507.01786","title":"Probing and Steering Evaluation Awareness of Language Models","created":"2025-07-02","cited_by_count":35,"area":null},{"id":"2504.21848","title":"Characterizing AI Agents for Alignment and Governance","created":"2025-04-30","cited_by_count":30,"area":null},{"id":"2509.14260","title":"Incomplete Tasks Induce Shutdown Resistance in Some Frontier LLMs","created":"2025-09-13","cited_by_count":22,"area":null},{"id":"2608.05466","title":"Recursive Synthesis for Long-Horizon Terminal Tasks","created":"2026-08-05","cited_by_count":19,"area":null},{"id":"2505.05602","title":"HiBayES: A Hierarchical Bayesian Modeling Framework for AI Evaluation Statistics","created":"2025-05-08","cited_by_count":18,"area":null},{"id":"2512.09187","title":"WOLF: Werewolf-based Observations for LLM Deception and Falsehoods","created":"2025-12-09","cited_by_count":13,"area":null},{"id":"2601.23045","title":"The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?","created":"2026-01-30","cited_by_count":10,"area":null},{"id":"2605.13625","title":"How to Interpret Agent Behavior","created":"2026-05-13","cited_by_count":10,"area":null},{"id":"2605.29548","title":"Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention","created":"2026-05-28","cited_by_count":10,"area":null},{"id":"2608.18580","title":"FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis","created":"2026-08-19","cited_by_count":9,"area":null},{"id":"2506.06414","title":"Benchmarking Misuse Mitigation Against Covert Adversaries","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2508.04586","title":"Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference","created":"2025-08-06","cited_by_count":8,"area":null},{"id":"2510.06824","title":"Efficient numeracy in language models through single-token number embeddings","created":"2025-10-08","cited_by_count":7,"area":null},{"id":"2604.21098","title":"Propensity Inference: Environmental Contributors to LLM Behaviour","created":"2026-04-22","cited_by_count":7,"area":null},{"id":"2602.07267","title":"BRIDGE: Predicting Human Task Completion Time From Model Performance","created":"2026-02-06","cited_by_count":6,"area":null},{"id":"2505.19915","title":"Evaluating AI cyber capabilities with crowdsourced elicitation","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2507.12872","title":"Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2507.15759","title":"Interaction as Intelligence: Deep Research With Human-AI Partnership","created":"2025-07-21","cited_by_count":5,"area":null},{"id":"2606.08529","title":"Scaffold Effects on GAIA: A Controlled Comparison","created":"2026-06-07","cited_by_count":5,"area":null},{"id":"2504.05755","title":"Unraveling Human-AI Teaming: A Review and Outlook","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2511.01348","title":"The Future of Generative AI in Software Engineering: A Vision from Industry and Academia in the European GENIUS Project","created":"2025-11-03","cited_by_count":4,"area":null},{"id":"2601.20886","title":"IDE-Bench: Evaluating Large Language Models as IDE Agents on Real-World Software Engineering Tasks","created":"2026-01-28","cited_by_count":4,"area":null},{"id":"2605.20520","title":"Open-World Evaluations for Measuring Frontier AI Capabilities","created":"2026-05-19","cited_by_count":4,"area":null},{"id":"2606.12683","title":"From AGI to ASI","created":"2026-06-10","cited_by_count":4,"area":null},{"id":"2511.19492","title":"Forecasting AI Time Horizon Under Compute Slowdowns","created":"2025-11-23","cited_by_count":3,"area":null},{"id":"2512.00742","title":"On the Regulatory Potential of User Interfaces for AI Agent Governance","created":"2025-11-30","cited_by_count":3,"area":null},{"id":"2604.00010","title":"Can LLMs Perceive Time? An Empirical Investigation","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2606.05342","title":"SentinelBench: A Benchmark for Long-Running Monitoring Agents","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2507.21839","title":"Against racing to AGI: Cooperation, deterrence, and catastrophic risks","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2508.15858","title":"Building and Measuring Trust between Large Language Models","created":"2025-08-20","cited_by_count":2,"area":null},{"id":"2511.00180","title":"ParaScopes: What do Language Models Activations Encode About Future Text?","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2512.21127","title":"A Real-World Evaluation of LLM Medication Safety Reviews in NHS Primary Care","created":"2025-12-24","cited_by_count":2,"area":null},{"id":"2605.12233","title":"No More, No Less: Task Alignment in Terminal Agents","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.15164","title":"Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2607.19321","title":"ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2609.01595","title":"Mechanism Design for Alignment and Control","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2506.00047","title":"Risks of AI-driven product development and strategies for their mitigation","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2507.06398","title":"Jolting Technologies: Superexponential Acceleration in AI Capabilities and Implications for AGI","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2602.04836","title":"Are AI Capabilities Increasing Exponentially? A Competing Hypothesis","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2604.01363","title":"Crashing Waves vs. Rising Tides: Findings on AI Automation from Thousands of Worker Evaluations of Labor Market Tasks","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2605.30628","title":"The Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.13892","title":"Crypto x AI, AI x Crypto: A Survey","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2607.27951","title":"Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.14426","title":"The Dynamics of Intelligence Explosions","created":"2026-08-14","cited_by_count":1,"area":null},{"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":"2512.00365","title":"Towards aligned body representations in vision models","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2601.11518","title":"How Long Is a Piece of String? A Brief Empirical Analysis of Tokenizers","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2603.14664","title":"Punctuated Equilibria in Artificial Intelligence: The Institutional Scaling Law and the Speciation of Sovereign AI","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2604.14990","title":"The Possibility of Artificial Intelligence Becoming a Subject and the Alignment Problem","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.23007","title":"MadEvolve: Evolutionary Optimization of Trading Systems with Large Language Models","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.07594","title":"Syll: Open-Source Personal Automation with Cross-Surface Execution","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.08629","title":"Sycophancy Towards Researchers Drives Performative Misalignment","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2607.00913","title":"Two AI Metrics Diverged: Will it Make All the Difference?","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.19375","title":"Economic Evaluations of Language Models","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.20444","title":"Confidently Deceptive: On the Relationship Between Confidence and Deception in LLMs","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2607.21547","title":"The Boundaries of Automation: A Theory of Persistent Human Participation","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.25891","title":"Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.27283","title":"Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.05797","title":"Predicting Task Difficulty Without Rollouts","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.00137","title":"Recursive Criticality of AI Self-Improvement","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.09059","title":"PlayTrain: An Efficient Reinforcement Learning Framework for LLM-Generated Adaptable JavaScript Games","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.15289","title":"Math for AI safety: an invitation for mathematicians","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2610.01306","title":"DAYJOB: A Benchmark for Long-Horizon Professional Work","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.06824","title":"TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.11539","title":"Design Creativity Bench: Measuring creativity in LLM-Generated UI","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.16280","title":"agent-risk: Risk Assessment for Changes to AI Agents","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}