{"total":62,"rows":[{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135,"area":"agents"},{"id":"2102.03896","title":"Consequences of Misaligned AI","created":"2021-02-07","cited_by_count":80,"area":null},{"id":"2408.16984","title":"Beyond Preferences in AI Alignment","created":"2024-08-30","cited_by_count":49,"area":"alignment"},{"id":"2405.17713","title":"AI Alignment with Changing and Influenceable Reward Functions","created":"2024-05-28","cited_by_count":33,"area":"alignment"},{"id":"2107.10939","title":"What are you optimizing for? Aligning Recommender Systems with Human Values","created":"2021-07-22","cited_by_count":29,"area":"alignment"},{"id":"2106.11022","title":"Hard Choices in Artificial Intelligence","created":"2021-06-10","cited_by_count":26,"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":"2209.13020","title":"Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans","created":"2022-09-14","cited_by_count":23,"area":null},{"id":"2405.08154","title":"LLM Theory of Mind and Alignment: Opportunities and Risks","created":"2024-05-13","cited_by_count":18,"area":"alignment"},{"id":"2509.01063","title":"An Economy of AI Agents","created":"2025-09-01","cited_by_count":18,"area":null},{"id":"2401.00298","title":"Principal-Agent Reward Shaping in MDPs","created":"2023-12-30","cited_by_count":13,"area":null},{"id":"2405.08597","title":"Risks and Opportunities of Open-Source Generative AI","created":"2024-05-14","cited_by_count":13,"area":null},{"id":"2504.03255","title":"Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective","created":"2025-04-04","cited_by_count":13,"area":"agents"},{"id":"2204.05151","title":"Metaethical Perspectives on 'Benchmarking' AI Ethics","created":"2022-04-11","cited_by_count":12,"area":null},{"id":"2307.02318","title":"Deep Contract Design via Discontinuous Networks","created":"2023-07-05","cited_by_count":11,"area":null},{"id":"2410.09638","title":"On Goodhart's law, with an application to value alignment","created":"2024-10-12","cited_by_count":9,"area":null},{"id":"2505.05197","title":"Societal and technological progress as sewing an ever-growing, ever-changing, patchy, and polychrome quilt","created":"2025-05-08","cited_by_count":9,"area":null},{"id":"2508.08544","title":"AI Agents and the Law","created":"2025-08-12","cited_by_count":9,"area":"agents"},{"id":"2308.02435","title":"Designing Fiduciary Artificial Intelligence","created":"2023-07-27","cited_by_count":8,"area":null},{"id":"2310.18244","title":"A Review of the Evidence for Existential Risk from AI via Misaligned Power-Seeking","created":"2023-10-27","cited_by_count":8,"area":null},{"id":"2503.00069","title":"Societal Alignment Frameworks Can Improve LLM Alignment","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2506.17434","title":"Resource Rational Contractualism Should Guide AI Alignment","created":"2025-06-20","cited_by_count":8,"area":null},{"id":"2512.03399","title":"Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value","created":"2025-12-03","cited_by_count":6,"area":null},{"id":"2311.17228","title":"Survey on AI Ethics: A Socio-technical Perspective","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2405.18510","title":"Improved Emotional Alignment of AI and Humans: Human Ratings of Emotions Expressed by Stable Diffusion v1, DALL-E 2, and DALL-E 3","created":"2024-05-28","cited_by_count":3,"area":"diffusion"},{"id":"2601.23211","title":"Multi-Agent Systems Should be Treated as Principal-Agent Problems","created":"2026-01-30","cited_by_count":3,"area":"agents"},{"id":"2102.00834","title":"Counterfactual Planning in AGI Systems","created":"2021-01-29","cited_by_count":2,"area":null},{"id":"2507.00631","title":"A Protocol for Trustless Verification Under Uncertainty","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2602.02572","title":"Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective","created":"2026-01-31","cited_by_count":2,"area":"alignment"},{"id":"2602.14606","title":"Towards Selection as Power: Bounding Decision Authority in Autonomous Agents","created":"2026-02-16","cited_by_count":2,"area":"agents"},{"id":"2604.21216","title":"Post-AGI Economies: Autonomy and the First Fundamental Theorem of Welfare Economics","created":"2026-04-23","cited_by_count":2,"area":null},{"id":"2605.01643","title":"AI Alignment via Incentives and Correction","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2207.00868","title":"The Linguistic Blind Spot of Value-Aligned Agency, Natural and Artificial","created":"2022-07-02","cited_by_count":1,"area":null},{"id":"2304.12241","title":"Positive AI: Key Challenges in Designing Artificial Intelligence for Wellbeing","created":"2023-04-12","cited_by_count":1,"area":null},{"id":"2408.08995","title":"On the Undecidability of Artificial Intelligence Alignment: Machines that Halt","created":"2024-08-16","cited_by_count":1,"area":"alignment"},{"id":"2510.09859","title":"Pricing Access to Dynamic Information Services","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2603.15017","title":"Consequentialist Objectives and Catastrophe","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2606.08267","title":"Post-AGI Economies: Superposition and the Second Fundamental Theorem of Welfare Economics","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2607.22750","title":"Commitment To Cooperation With Self-Negotiated Contracts","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2112.10190","title":"Demanding and Designing Aligned Cognitive Architectures","created":"2021-12-19","cited_by_count":0,"area":null},{"id":"2208.12299","title":"Modelling the Recommender Alignment Problem","created":"2022-08-25","cited_by_count":0,"area":null},{"id":"2303.12350","title":"Artificial Intelligence and Dual Contract","created":"2023-03-22","cited_by_count":0,"area":null},{"id":"2310.05871","title":"Dynamic value alignment through preference aggregation of multiple objectives","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2409.18995","title":"Systematic Characterization of the Effectiveness of Alignment in Large Language Models for Categorical Decisions","created":"2024-09-18","cited_by_count":0,"area":"alignment"},{"id":"2504.15304","title":"AI Agents and Hard Choices","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2506.08998","title":"On Monotonicity in AI Alignment","created":"2025-06-10","cited_by_count":0,"area":"alignment"},{"id":"2509.07642","title":"Getting In Contract with Large Language Models -- An Agency Theory Perspective On Large Language Model Alignment","created":"2025-09-09","cited_by_count":0,"area":"alignment"},{"id":"2509.10780","title":"Bridging Cultural Distance Between Models Default and Local Classroom Demands: How Global Teachers Adopt GenAI to Support Everyday Teaching Practices","created":"2025-09-13","cited_by_count":0,"area":null},{"id":"2510.15395","title":"Corrigibility Transformation: Constructing Goals That Accept Updates","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2510.27628","title":"Validity Is What You Need","created":"2025-10-31","cited_by_count":0,"area":"agents"},{"id":"2602.21401","title":"The Headless Firm: How AI Reshapes Enterprise Boundaries","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2603.02019","title":"Selection as Power: Constrained Reinforcement for Bounded Decision Authority","created":"2026-03-02","cited_by_count":0,"area":"agents"},{"id":"2604.20805","title":"Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.25739","title":"The Behavioral Credibility Trilemma: When Calibrated Autonomy Becomes Impossible","created":"2026-05-25","cited_by_count":0,"area":"deeprl"},{"id":"2606.22797","title":"Measuring Behavior Portability in Large Language Models","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.28881","title":"Fragility of Value under Imperfect Alignment","created":"2026-07-30","cited_by_count":0,"area":"alignment"},{"id":"2608.10475","title":"Evaluating Rational Contracting in Natural Language","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.15403","title":"Agent Inheritance Protocol: Speculating on Feralized Agents After Principals Die","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2609.12039","title":"Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering","created":"2026-09-10","cited_by_count":0,"area":"agents"},{"id":"2609.38262","title":"When Does Randomized Oversight Align AI Agents That Can Conceal?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.17062","title":"Gradient Routing Localizes and Removes Unintended Behaviors in RL","created":"2026-10-12","cited_by_count":0,"area":"alignment"},{"id":"2610.19832","title":"Rent-Seeking Language Models: Reward Models Set the Prices, Frequent Audits Curb the Rent","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}