{"total":110,"rows":[{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802,"area":null},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371,"area":null},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2310.12567","title":"Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark","created":"2023-10-19","cited_by_count":143,"area":null},{"id":"2102.03896","title":"Consequences of Misaligned AI","created":"2021-02-07","cited_by_count":80,"area":null},{"id":"2305.16960","title":"Training Socially Aligned Language Models on Simulated Social Interactions","created":"2023-05-26","cited_by_count":78,"area":"alignment"},{"id":"2002.09089","title":"Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences","created":"2020-02-21","cited_by_count":73,"area":"offlinerl"},{"id":"2503.03480","title":"SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning","created":"2025-03-05","cited_by_count":72,"area":"vla"},{"id":"2210.12530","title":"LMPriors: Pre-Trained Language Models as Task-Specific Priors","created":"2022-10-22","cited_by_count":56,"area":null},{"id":"2112.15422","title":"Scalar reward is not enough: A response to Silver, Singh, Precup and Sutton (2021)","created":"2021-11-25","cited_by_count":55,"area":null},{"id":"2109.06325","title":"safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics","created":"2021-09-13","cited_by_count":50,"area":null},{"id":"2401.16635","title":"Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble","created":"2024-01-30","cited_by_count":44,"area":"alignment"},{"id":"2209.08025","title":"Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2502.12081","title":"Unhackable Temporal Rewarding for Scalable Video MLLMs","created":"2025-02-17","cited_by_count":33,"area":null},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2205.01975","title":"Aligning to Social Norms and Values in Interactive Narratives","created":"2022-05-04","cited_by_count":32,"area":null},{"id":"2106.04823","title":"Taxonomy of Machine Learning Safety: A Survey and Primer","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2106.00099","title":"Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs","created":"2021-05-31","cited_by_count":22,"area":"offlinerl"},{"id":"2311.00710","title":"Interactive AI Alignment: Specification, Process, and Evaluation Alignment","created":"2023-10-23","cited_by_count":22,"area":null},{"id":"2401.10899","title":"Concrete Problems in AI Safety, Revisited","created":"2023-12-18","cited_by_count":22,"area":null},{"id":"2403.04471","title":"The Shutdown Problem: An AI Engineering Puzzle for Decision Theorists","created":"2024-03-07","cited_by_count":22,"area":null},{"id":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20,"area":"offlinerl"},{"id":"2109.05439","title":"Concave Utility Reinforcement Learning with Zero-Constraint Violations","created":"2021-09-12","cited_by_count":19,"area":null},{"id":"2106.04480","title":"There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2602.11865","title":"Intelligent AI Delegation","created":"2026-02-12","cited_by_count":18,"area":null},{"id":"2104.09469","title":"Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior","created":"2021-04-19","cited_by_count":14,"area":null},{"id":"2505.17342","title":"A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safety","created":"2025-05-22","cited_by_count":13,"area":null},{"id":"1905.09710","title":"Inverse Reinforcement Learning in Contextual MDPs","created":"2019-05-23","cited_by_count":12,"area":"offlinerl"},{"id":"2210.06380","title":"Near-Optimal Multi-Agent Learning for Safe Coverage Control","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2306.17279","title":"Probabilistic Constraint for Safety-Critical Reinforcement Learning","created":"2023-06-29","cited_by_count":11,"area":null},{"id":"2407.09221","title":"Evaluating AI Evaluation: Perils and Prospects","created":"2024-07-12","cited_by_count":11,"area":null},{"id":"2603.15381","title":"Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science","created":"2026-03-16","cited_by_count":11,"area":null},{"id":"2102.07716","title":"How RL Agents Behave When Their Actions Are Modified","created":"2021-02-15","cited_by_count":10,"area":null},{"id":"2305.19861","title":"Human Control: Definitions and Algorithms","created":"2023-05-31","cited_by_count":10,"area":null},{"id":"2308.02435","title":"Designing Fiduciary Artificial Intelligence","created":"2023-07-27","cited_by_count":8,"area":null},{"id":"2409.08212","title":"Adaptive Language-Guided Abstraction from Contrastive Explanations","created":"2024-09-12","cited_by_count":8,"area":null},{"id":"2111.02907","title":"Model-Free Risk-Sensitive Reinforcement Learning","created":"2021-11-04","cited_by_count":7,"area":null},{"id":"2312.01818","title":"Hybrid Approaches for Moral Value Alignment in AI Agents: a Manifesto","created":"2023-12-04","cited_by_count":7,"area":"agents"},{"id":"2604.01476","title":"From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation Engineering","created":"2026-04-01","cited_by_count":7,"area":"alignment"},{"id":"2104.12582","title":"Understanding and Avoiding AI Failures: A Practical Guide","created":"2021-04-22","cited_by_count":6,"area":null},{"id":"2310.06775","title":"Conceptual Framework for Autonomous Cognitive Entities","created":"2023-10-03","cited_by_count":6,"area":"agents"},{"id":"2503.08241","title":"HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents","created":"2025-03-11","cited_by_count":6,"area":"deeprl"},{"id":"2511.02109","title":"Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences","created":"2025-11-03","cited_by_count":6,"area":"alignment"},{"id":"2105.06551","title":"Axes for Sociotechnical Inquiry in AI Research","created":"2021-04-26","cited_by_count":5,"area":null},{"id":"2108.13980","title":"Incorporating Deception into CyberBattleSim for Autonomous Defense","created":"2021-08-31","cited_by_count":5,"area":null},{"id":"2208.13687","title":"Categorical semantics of compositional reinforcement learning","created":"2022-08-29","cited_by_count":5,"area":null},{"id":"2210.00596","title":"Policy Gradients for Probabilistic Constrained Reinforcement Learning","created":"2022-10-02","cited_by_count":5,"area":null},{"id":"2603.25681","title":"Self-Improvement of Large Language Models: A Technical Overview and Future Outlook","created":"2026-03-26","cited_by_count":5,"area":"synth"},{"id":"2103.03938","title":"Causal Analysis of Agent Behavior for AI Safety","created":"2021-03-05","cited_by_count":4,"area":null},{"id":"2301.11592","title":"Solving Richly Constrained Reinforcement Learning through State Augmentation and Reward Penalties","created":"2023-01-27","cited_by_count":4,"area":null},{"id":"2304.08845","title":"Feasible Policy Iteration for Safe Reinforcement Learning","created":"2023-04-18","cited_by_count":4,"area":null},{"id":"2402.04182","title":"Reinforcement Learning with Ensemble Model Predictive Safety Certification","created":"2024-02-06","cited_by_count":4,"area":"deeprl"},{"id":"2502.20341","title":"Safety Representations for Safer Policy Learning","created":"2025-02-27","cited_by_count":4,"area":"deeprl"},{"id":"2508.09128","title":"A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functions","created":"2025-08-12","cited_by_count":4,"area":"deeprl"},{"id":"2509.10423","title":"Mutual Information Tracks Policy Coherence in Reinforcement Learning","created":"2025-09-12","cited_by_count":4,"area":"deeprl"},{"id":"2110.15907","title":"Learning to Be Cautious","created":"2021-10-29","cited_by_count":3,"area":null},{"id":"2206.11812","title":"Formalizing the Problem of Side Effect Regularization","created":"2022-06-23","cited_by_count":3,"area":null},{"id":"2304.13616","title":"CROP: Towards Distributional-Shift Robust Reinforcement Learning using Compact Reshaped Observation Processing","created":"2023-04-26","cited_by_count":3,"area":null},{"id":"2602.14135","title":"ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI","created":"2026-02-15","cited_by_count":3,"area":null},{"id":"2204.09622","title":"A Brief Guide to Designing and Evaluating Human-Centered Interactive Machine Learning","created":"2022-04-20","cited_by_count":2,"area":null},{"id":"2207.08651","title":"Boolean Decision Rules for Reinforcement Learning Policy Summarisation","created":"2022-07-18","cited_by_count":2,"area":null},{"id":"2303.03174","title":"Both eyes open: Vigilant Incentives help Regulatory Markets improve AI Safety","created":"2023-03-06","cited_by_count":2,"area":null},{"id":"2312.09402","title":"CERN for AI: A Theoretical Framework for Autonomous Simulation-Based Artificial Intelligence Testing and Alignment","created":"2023-12-14","cited_by_count":2,"area":null},{"id":"2504.03185","title":"Learning Natural Language Constraints for Safe Reinforcement Learning of Language Agents","created":"2025-04-04","cited_by_count":2,"area":"agents"},{"id":"2506.02357","title":"Evaluating LLM Agent Adherence to Hierarchical Safety Principles: A Lightweight Benchmark for Probing Foundational Controllability Components","created":"2025-06-03","cited_by_count":2,"area":"agents"},{"id":"2603.26725","title":"Capability Safety as Datalog: A Foundational Equivalence","created":"2026-03-20","cited_by_count":2,"area":null},{"id":"2604.12086","title":"Robust Optimization for Mitigating Reward Hacking with Correlated Proxies","created":"2026-04-13","cited_by_count":2,"area":"alignment"},{"id":"2605.03512","title":"Brainrot: Deskilling and Addiction are Overlooked AI Risks","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2606.20376","title":"CRAX: Fast Safe Reinforcement Learning Benchmarking","created":"2026-06-18","cited_by_count":2,"area":"deeprl"},{"id":"2608.04574","title":"When Memory Lies: An Empirical Study of Spatial Memory Staleness in VLM Agents","created":"2026-08-05","cited_by_count":2,"area":"agents"},{"id":"2112.08736","title":"Learning to Minimize Cost-to-Serve for Multi-Node Multi-Product Order Fulfilment in Electronic Commerce","created":"2021-12-16","cited_by_count":1,"area":null},{"id":"2201.06274","title":"Detecting danger in gridworlds using Gromov's Link Condition","created":"2022-01-17","cited_by_count":1,"area":null},{"id":"2204.11142","title":"Graph Neural Network based Agent in Google Research Football","created":"2022-04-23","cited_by_count":1,"area":null},{"id":"2209.03596","title":"An Empirical Evaluation of Posterior Sampling for Constrained Reinforcement Learning","created":"2022-09-08","cited_by_count":1,"area":null},{"id":"2306.02979","title":"The Chai Platform's AI Safety Framework","created":"2023-06-05","cited_by_count":1,"area":null},{"id":"2309.16166","title":"CoinRun: Solving Goal Misgeneralisation","created":"2023-09-28","cited_by_count":1,"area":null},{"id":"2404.15184","title":"Reducing Human-Robot Goal State Divergence with Environment Design","created":"2024-04-10","cited_by_count":1,"area":null},{"id":"2506.17792","title":"Accelerating Policy Synthesis in Large-Scale MDPs via Hierarchical Adaptive Refinement","created":"2025-06-21","cited_by_count":1,"area":null},{"id":"2508.05766","title":"A Framework for Inherently Safer AGI through Language-Mediated Active Inference","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2510.13036","title":"Repairing Reward Functions with Feedback to Mitigate Reward Hacking","created":"2025-10-14","cited_by_count":1,"area":"alignment"},{"id":"2511.21531","title":"Predictive Safety Shield for Dyna-Q Reinforcement Learning","created":"2025-11-26","cited_by_count":1,"area":"deeprl"},{"id":"2603.15017","title":"Consequentialist Objectives and Catastrophe","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2605.05921","title":"Intentmaking and Sensemaking: Human Interaction with AI-Guided Mathematical Discovery","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2607.22188","title":"Draining the Energy Commons: Self-Defeating Over-Appropriation as a Coordination Failure in Agentic LLM Collectives","created":"2026-07-24","cited_by_count":1,"area":"agents"},{"id":"2608.03562","title":"Robust General Utility for Reinforcement Learning","created":"2026-08-04","cited_by_count":1,"area":"deeprl"},{"id":"2609.11028","title":"BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure","created":"2026-09-10","cited_by_count":1,"area":"agents"},{"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":"1809.01036","title":"A Roadmap for Robust End-to-End Alignment","created":"2018-09-04","cited_by_count":0,"area":"alignment"},{"id":"1912.08444","title":"Relational Mimic for Visual Adversarial Imitation Learning","created":"2019-12-18","cited_by_count":0,"area":"offlinerl"},{"id":"2306.00380","title":"Survey of Trustworthy AI: A Meta Decision of AI","created":"2023-06-01","cited_by_count":0,"area":null},{"id":"2308.12918","title":"Evaluating the Vulnerabilities in ML systems in terms of adversarial attacks","created":"2023-08-24","cited_by_count":0,"area":null},{"id":"2309.15737","title":"Provably Efficient Exploration in Constrained Reinforcement Learning:Posterior Sampling Is All You Need","created":"2023-09-27","cited_by_count":0,"area":null},{"id":"2412.03058","title":"Revisiting Energy-Based Model for Out-of-Distribution Detection","created":"2024-12-04","cited_by_count":0,"area":null},{"id":"2502.09583","title":"YRC-Bench: A Benchmark for Learning to Coordinate with Experts","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2506.01813","title":"The Ultimate Test of Superintelligent AI Agents: Can an AI Balance Care and Control in Asymmetric Relationships?","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2510.16185","title":"Expressive Reward Synthesis with the Runtime Monitoring Language","created":"2025-10-17","cited_by_count":0,"area":"deeprl"},{"id":"2511.12808","title":"Expressive Temporal Specifications for Reward Monitoring","created":"2025-11-16","cited_by_count":0,"area":"deeprl"},{"id":"2602.12124","title":"Alignment Risks from Capability-Seeking RL Training","created":"2026-02-12","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}