{"total":300,"rows":[{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912,"area":"alignment"},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395,"area":"agents"},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531,"area":"agents"},{"id":"1811.06711","title":"An Algorithmic Perspective on Imitation Learning","created":"2018-11-16","cited_by_count":459,"area":"offlinerl"},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2209.13085","title":"Defining and Characterizing Reward Hacking","created":"2022-09-27","cited_by_count":203,"area":"alignment"},{"id":"2304.03279","title":"Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark","created":"2023-04-06","cited_by_count":182,"area":null},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2306.15448","title":"Understanding Social Reasoning in Language Models with Language Models","created":"2023-06-21","cited_by_count":172,"area":"lr"},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2309.02473","title":"A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges","created":"2023-09-05","cited_by_count":148,"area":"offlinerl"},{"id":"2210.01790","title":"Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals","created":"2022-10-04","cited_by_count":126,"area":null},{"id":"2012.06733","title":"Human-in-the-Loop Imitation Learning using Remote Teleoperation","created":"2020-12-12","cited_by_count":112,"area":"offlinerl"},{"id":"1807.09936","title":"Multi-Agent Generative Adversarial Imitation Learning","created":"2018-07-26","cited_by_count":100,"area":"offlinerl"},{"id":"2212.09746","title":"Evaluating Human-Language Model Interaction","created":"2022-12-19","cited_by_count":92,"area":null},{"id":"2310.11589","title":"Eliciting Human Preferences with Language Models","created":"2023-10-17","cited_by_count":92,"area":null},{"id":"2401.08743","title":"MMToM-QA: Multimodal Theory of Mind Question Answering","created":"2024-01-16","cited_by_count":85,"area":null},{"id":"2102.03896","title":"Consequences of Misaligned AI","created":"2021-02-07","cited_by_count":80,"area":null},{"id":"2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","created":"2024-06-06","cited_by_count":80,"area":null},{"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":"2408.03943","title":"Building Machines that Learn and Think with People","created":"2024-07-22","cited_by_count":73,"area":null},{"id":"2111.00876","title":"On the Expressivity of Markov Reward","created":"2021-11-01","cited_by_count":71,"area":null},{"id":"2011.04709","title":"f-IRL: Inverse Reinforcement Learning via State Marginal Matching","created":"2020-11-09","cited_by_count":67,"area":"offlinerl"},{"id":"2502.08640","title":"Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs","created":"2025-02-12","cited_by_count":67,"area":"agents"},{"id":"2206.15474","title":"Forecasting Future World Events with Neural Networks","created":"2022-06-30","cited_by_count":63,"area":null},{"id":"2312.05230","title":"Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning","created":"2023-12-08","cited_by_count":60,"area":"wm"},{"id":"2110.13136","title":"What Would Jiminy Cricket Do? Towards Agents That Behave Morally","created":"2021-10-25","cited_by_count":57,"area":null},{"id":"2502.02528","title":"Why human-AI relationships need socioaffective alignment","created":"2025-02-04","cited_by_count":47,"area":null},{"id":"2102.12321","title":"AGENT: A Benchmark for Core Psychological Reasoning","created":"2021-02-24","cited_by_count":42,"area":null},{"id":"2310.13595","title":"The History and Risks of Reinforcement Learning and Human Feedback","created":"2023-10-20","cited_by_count":42,"area":"alignment"},{"id":"2009.14715","title":"Learning Rewards from Linguistic Feedback","created":"2020-09-30","cited_by_count":41,"area":"alignment"},{"id":"2501.10114","title":"Infrastructure for AI Agents","created":"2025-01-17","cited_by_count":41,"area":null},{"id":"2211.13746","title":"Melting Pot 2.0","created":"2022-11-24","cited_by_count":40,"area":null},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38,"area":null},{"id":"2302.01605","title":"Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased","created":"2023-02-03","cited_by_count":37,"area":null},{"id":"2205.01975","title":"Aligning to Social Norms and Values in Interactive Narratives","created":"2022-05-04","cited_by_count":32,"area":null},{"id":"2305.20076","title":"Decision-Oriented Dialogue for Human-AI Collaboration","created":"2023-05-31","cited_by_count":29,"area":null},{"id":"2505.18807","title":"Mitigating Deceptive Alignment via Self-Monitoring","created":"2025-05-24","cited_by_count":29,"area":"lr"},{"id":"1805.07687","title":"Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications","created":"2018-05-20","cited_by_count":28,"area":"offlinerl"},{"id":"2110.04186","title":"Medical Dead-ends and Learning to Identify High-risk States and Treatments","created":"2021-10-08","cited_by_count":28,"area":null},{"id":"2208.08345","title":"Discovering Agents","created":"2022-08-17","cited_by_count":28,"area":null},{"id":"2402.17930","title":"Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planning","created":"2024-02-27","cited_by_count":28,"area":null},{"id":"2212.03201","title":"Misspecification in Inverse Reinforcement Learning","created":"2022-12-06","cited_by_count":27,"area":"offlinerl"},{"id":"2102.08492","title":"Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments","created":"2021-02-16","cited_by_count":26,"area":null},{"id":"2106.11022","title":"Hard Choices in Artificial Intelligence","created":"2021-06-10","cited_by_count":26,"area":null},{"id":"2306.06924","title":"TASRA: a Taxonomy and Analysis of Societal-Scale Risks from AI","created":"2023-06-12","cited_by_count":26,"area":null},{"id":"2111.06956","title":"Human irrationality: both bad and good for reward inference","created":"2021-11-12","cited_by_count":25,"area":null},{"id":"2201.00012","title":"MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning","created":"2021-12-30","cited_by_count":25,"area":"alignment"},{"id":"1905.11867","title":"Interactive Teaching Algorithms for Inverse Reinforcement Learning","created":"2019-05-28","cited_by_count":24,"area":"offlinerl"},{"id":"2301.05223","title":"NOPA: Neurally-guided Online Probabilistic Assistance for Building Socially Intelligent Home Assistants","created":"2023-01-12","cited_by_count":23,"area":null},{"id":"2406.01309","title":"REvolve: Reward Evolution with Large Language Models using Human Feedback","created":"2024-06-03","cited_by_count":23,"area":"alignment"},{"id":"2502.15676","title":"AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling","created":"2025-02-21","cited_by_count":23,"area":"agents"},{"id":"2109.00127","title":"Cognitive science as a source of forward and inverse models of human decisions for robotics and control","created":"2021-09-01","cited_by_count":22,"area":null},{"id":"2206.07870","title":"How to talk so AI will learn: Instructions, descriptions, and autonomy","created":"2022-06-16","cited_by_count":22,"area":null},{"id":"2206.13316","title":"Humans are not Boltzmann Distributions: Challenges and Opportunities for Modelling Human Feedback and Interaction in Reinforcement Learning","created":"2022-06-27","cited_by_count":22,"area":null},{"id":"2408.03029","title":"Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning","created":"2024-08-06","cited_by_count":22,"area":"deeprl"},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21,"area":"alignment"},{"id":"2210.02667","title":"A Human Rights-Based Approach to Responsible AI","created":"2022-10-06","cited_by_count":20,"area":null},{"id":"1912.03553","title":"Learning Norms from Stories: A Prior for Value Aligned Agents","created":"2019-12-07","cited_by_count":19,"area":"alignment"},{"id":"2107.02349","title":"Physical Interaction as Communication: Learning Robot Objectives Online from Human Corrections","created":"2021-07-06","cited_by_count":19,"area":null},{"id":"2507.05619","title":"Detecting Proxy Gaming in RL and LLM Alignment via Evaluator Stress Tests","created":"2025-07-08","cited_by_count":19,"area":"alignment"},{"id":"1906.00429","title":"Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints","created":"2019-06-02","cited_by_count":18,"area":"offlinerl"},{"id":"2112.01298","title":"Meaningful human control: actionable properties for AI system development","created":"2021-11-25","cited_by_count":18,"area":null},{"id":"2304.12529","title":"Improved Trust in Human-Robot Collaboration with ChatGPT","created":"2023-04-25","cited_by_count":18,"area":null},{"id":"2306.01804","title":"Extracting Reward Functions from Diffusion Models","created":"2023-06-01","cited_by_count":18,"area":"diffusion"},{"id":"2405.08154","title":"LLM Theory of Mind and Alignment: Opportunities and Risks","created":"2024-05-13","cited_by_count":18,"area":"alignment"},{"id":"2306.14858","title":"Proportional Aggregation of Preferences for Sequential Decision Making","created":"2023-06-26","cited_by_count":17,"area":null},{"id":"2306.16207","title":"Inferring the Goals of Communicating Agents from Actions and Instructions","created":"2023-06-28","cited_by_count":17,"area":"agents"},{"id":"2402.17747","title":"When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback","created":"2024-02-27","cited_by_count":17,"area":"alignment"},{"id":"2508.18765","title":"Governance-as-a-Service: A Multi-Agent Framework for AI System Compliance and Policy Enforcement","created":"2025-08-26","cited_by_count":17,"area":null},{"id":"2011.08541","title":"Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization","created":"2020-11-17","cited_by_count":16,"area":"offlinerl"},{"id":"2403.11075","title":"GOMA: Proactive Embodied Cooperative Communication via Goal-Oriented Mental Alignment","created":"2024-03-17","cited_by_count":16,"area":null},{"id":"1806.03820","title":"An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning","created":"2018-06-11","cited_by_count":15,"area":"offlinerl"},{"id":"2101.04237","title":"Solving Common-Payoff Games with Approximate Policy Iteration","created":"2021-01-11","cited_by_count":15,"area":null},{"id":"2103.16033","title":"FaiR-IoT: Fairness-aware Human-in-the-Loop Reinforcement Learning for Harnessing Human Variability in Personalized IoT","created":"2021-03-30","cited_by_count":15,"area":null},{"id":"2109.04307","title":"OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching","created":"2021-09-09","cited_by_count":15,"area":"offlinerl"},{"id":"2109.11328","title":"Reinforcement Learning Under Algorithmic Triage","created":"2021-09-23","cited_by_count":15,"area":null},{"id":"2202.00881","title":"Robustness and Adaptability of Reinforcement Learning based Cooperative Autonomous Driving in Mixed-autonomy Traffic","created":"2022-02-02","cited_by_count":15,"area":"driving"},{"id":"2407.10583","title":"Three Dogmas of Reinforcement Learning","created":"2024-07-15","cited_by_count":14,"area":"deeprl"},{"id":"2101.07691","title":"Choice Set Misspecification in Reward Inference","created":"2021-01-19","cited_by_count":13,"area":"alignment"},{"id":"2107.05825","title":"Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks","created":"2021-07-13","cited_by_count":13,"area":null},{"id":"2405.10729","title":"Contestable AI needs Computational Argumentation","created":"2024-05-17","cited_by_count":13,"area":null},{"id":"2411.02623","title":"Learning to Assist Humans without Inferring Rewards","created":"2024-11-04","cited_by_count":13,"area":"deeprl"},{"id":"2412.16468","title":"The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment","created":"2024-12-21","cited_by_count":13,"area":"alignment"},{"id":"2211.08371","title":"Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches","created":"2022-11-15","cited_by_count":12,"area":null},{"id":"2405.04495","title":"Toward In-Context Teaching: Adapting Examples to Students' Misconceptions","created":"2024-05-07","cited_by_count":12,"area":null},{"id":"2512.15712","title":"Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants","created":"2025-12-17","cited_by_count":12,"area":null},{"id":"2408.07461","title":"Problem Solving Through Human-AI Preference-Based Cooperation","created":"2024-08-14","cited_by_count":11,"area":null},{"id":"2412.08812","title":"Test-Time Alignment via Hypothesis Reweighting","created":"2024-12-11","cited_by_count":11,"area":"alignment"},{"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":"2305.19861","title":"Human Control: Definitions and Algorithms","created":"2023-05-31","cited_by_count":10,"area":null},{"id":"2308.00031","title":"Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges","created":"2023-07-31","cited_by_count":10,"area":null},{"id":"2401.08672","title":"Concept Alignment","created":"2024-01-09","cited_by_count":10,"area":"alignment"},{"id":"2503.05996","title":"Towards Improving Reward Design in RL: A Reward Alignment Metric for RL Practitioners","created":"2025-03-08","cited_by_count":10,"area":null},{"id":"2504.07091","title":"AssistanceZero: Scalably Solving Assistance Games","created":"2025-04-09","cited_by_count":10,"area":"alignment"},{"id":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"id":"2303.11594","title":"A Review on Machine Theory of Mind","created":"2023-03-21","cited_by_count":9,"area":null},{"id":"2402.17975","title":"Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards","created":"2024-02-28","cited_by_count":9,"area":"alignment"}],"next_cursor":"100"}