{"total":78,"rows":[{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095,"area":"alignment"},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316,"area":"alignment"},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258,"area":null},{"id":"2310.02743","title":"Reward Model Ensembles Help Mitigate Overoptimization","created":"2023-10-04","cited_by_count":231,"area":"alignment"},{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188,"area":null},{"id":"2302.06692","title":"Guiding Pretraining in Reinforcement Learning with Large Language Models","created":"2023-02-13","cited_by_count":187,"area":null},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"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":"2204.01467","title":"On scientific understanding with artificial intelligence","created":"2022-04-04","cited_by_count":70,"area":null},{"id":"2306.01711","title":"OMNI: Open-endedness via Models of human Notions of Interestingness","created":"2023-06-02","cited_by_count":70,"area":null},{"id":"2405.01576","title":"Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant","created":"2024-04-25","cited_by_count":38,"area":null},{"id":"2301.13261","title":"Emergence of Maps in the Memories of Blind Navigation Agents","created":"2023-01-30","cited_by_count":33,"area":null},{"id":"2410.05584","title":"Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?","created":"2024-10-08","cited_by_count":31,"area":"lr"},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"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":"2205.10752","title":"Covariance Matrix Adaptation MAP-Annealing","created":"2022-05-22","cited_by_count":25,"area":null},{"id":"2203.16540","title":"Mind the gap: Challenges of deep learning approaches to Theory of Mind","created":"2022-03-30","cited_by_count":21,"area":null},{"id":"2302.03086","title":"DITTO: Offline Imitation Learning with World Models","created":"2023-02-06","cited_by_count":21,"area":"wm"},{"id":"2405.15815","title":"A social path to human-like artificial intelligence","created":"2024-05-22","cited_by_count":20,"area":null},{"id":"2405.04325","title":"Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation","created":"2024-05-07","cited_by_count":10,"area":null},{"id":"2106.04235","title":"Definitions of intent suitable for algorithms","created":"2021-06-08","cited_by_count":8,"area":null},{"id":"2406.19963","title":"Text2Robot: Evolutionary Robot Design from Text Descriptions","created":"2024-06-28","cited_by_count":8,"area":null},{"id":"2407.09502","title":"From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models","created":"2024-06-14","cited_by_count":8,"area":null},{"id":"2510.01925","title":"Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey","created":"2025-10-02","cited_by_count":8,"area":"lr"},{"id":"2503.05748","title":"Alignment, Agency and Autonomy in Frontier AI: A Systems Engineering Perspective","created":"2025-02-20","cited_by_count":7,"area":null},{"id":"2104.12582","title":"Understanding and Avoiding AI Failures: A Practical Guide","created":"2021-04-22","cited_by_count":6,"area":null},{"id":"2309.06717","title":"Bias Amplification Enhances Minority Group Performance","created":"2023-09-13","cited_by_count":6,"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":"2303.12803","title":"Evolving Populations of Diverse RL Agents with MAP-Elites","created":"2023-03-09","cited_by_count":5,"area":null},{"id":"2506.13834","title":"Evolvable Conditional Diffusion","created":"2025-06-16","cited_by_count":5,"area":null},{"id":"2206.06674","title":"Severe Damage Recovery in Evolving Soft Robots through Differentiable Programming","created":"2022-06-14","cited_by_count":4,"area":null},{"id":"2206.14135","title":"Towards Explainable Metaheuristic: Mining Surrogate Fitness Models for Importance of Variables","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2506.05070","title":"RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation","created":"2025-06-05","cited_by_count":4,"area":"alignment"},{"id":"2107.05786","title":"Carle's Game: An Open-Ended Challenge in Exploratory Machine Creativity","created":"2021-07-13","cited_by_count":3,"area":null},{"id":"2203.13050","title":"Evolved Open-Endedness in Cultural Evolution: A New Dimension in Open-Ended Evolution Research","created":"2022-03-24","cited_by_count":3,"area":null},{"id":"2302.09248","title":"Machine Love","created":"2023-02-18","cited_by_count":3,"area":null},{"id":"2209.01020","title":"EvolvingBehavior: Towards Co-Creative Evolution of Behavior Trees for Game NPCs","created":"2022-09-01","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":"2401.03529","title":"Quantifying stability of non-power-seeking in artificial agents","created":"2024-01-07","cited_by_count":2,"area":"agents"},{"id":"2404.17688","title":"Seizing the Means of Production: Exploring the Landscape of Crafting, Adapting and Navigating Generative AI Models in the Visual Arts","created":"2024-04-26","cited_by_count":2,"area":null},{"id":"2406.07811","title":"Evolutionary Computation and Explainable AI: A Roadmap to Understandable Intelligent Systems","created":"2024-06-12","cited_by_count":2,"area":null},{"id":"2501.15001","title":"What if Eye...? Computationally Recreating Vision Evolution","created":"2025-01-25","cited_by_count":2,"area":null},{"id":"2103.10790","title":"Quality Evolvability ES: Evolving Individuals With a Distribution of Well Performing and Diverse Offspring","created":"2021-03-19","cited_by_count":1,"area":null},{"id":"2205.07592","title":"Qualitative Differences Between Evolutionary Strategies and Reinforcement Learning Methods for Control of Autonomous Agents","created":"2022-05-16","cited_by_count":1,"area":null},{"id":"2405.18016","title":"On Creativity and Open-Endedness","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2411.01008","title":"AI-Guided Codesign Framework for Novel Material and Device Design applied to MTJ-based True Random Number Generators","created":"2024-11-01","cited_by_count":1,"area":null},{"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":"2606.11417","title":"Signed Compression Progress on a Sealed Audit is Goodhart-Resistant","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2607.01047","title":"Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates","created":"2026-07-01","cited_by_count":1,"area":"agents"},{"id":"2607.12488","title":"Sample Efficient Generative Optimization for Molecular Design","created":"2026-07-14","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":"2203.03480","title":"Reinforcement Learning for Location-Aware Scheduling","created":"2022-03-07","cited_by_count":0,"area":null},{"id":"2205.10118","title":"An Artificial Neural Network Functionalized by Evolution","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2303.15896","title":"Efficient Quality Diversity Optimization of 3D Buildings through 2D Pre-optimization","created":"2023-03-28","cited_by_count":0,"area":null},{"id":"2310.05430","title":"Replication of Multi-agent Reinforcement Learning for the \"Hide and Seek\" Problem","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2403.05540","title":"Extinction Risks from AI: Invisible to Science?","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2403.13950","title":"Evo* 2023 -- Late-Breaking Abstracts Volume","created":"2024-03-20","cited_by_count":0,"area":null},{"id":"2404.08991","title":"Business models for the simulation hypothesis","created":"2024-04-13","cited_by_count":0,"area":null},{"id":"2409.18982","title":"Aligning Robot Navigation Behaviors with Human Intentions and Preferences","created":"2024-09-16","cited_by_count":0,"area":null},{"id":"2411.00156","title":"Unlocking the Potential of Global Human Expertise","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2503.15514","title":"Superhuman Game AI Disclosure: Expertise and Context Moderate Effects on Trust and Fairness","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2505.16388","title":"Serious Games: Human-AI Interaction, Evolution, and Coevolution","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2508.06592","title":"Towards Integrated Alignment","created":"2025-08-08","cited_by_count":0,"area":"alignment"},{"id":"2510.08590","title":"Evolutionary Computation as Natural Generative AI","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2512.05212","title":"On the Computability of Artificial General Intelligence","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2601.17577","title":"Status Hierarchies in Language Models","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2603.12305","title":"HCP-DCNet: A Hierarchical Causal Primitive Dynamic Composition Network for Self-Improving Causal Understanding","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2603.14417","title":"Questionnaire Responses Do not Capture the Safety of AI Agents","created":"2026-03-15","cited_by_count":0,"area":"agents"},{"id":"2605.24096","title":"The Time is Here for Just-in-Time Systems: Challenges and Opportunities","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.16914","title":"Greed Is Learned: Visible Incentives as Reward-Hacking Triggers","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.29119","title":"Knowing in Advance When an Evolutionary Outer Loop Will Not Help: A Pre-Registered Cheap-Baseline Screening Rule","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.12986","title":"Win by Silence: Deletion Non-Monotonicity, Autonomous Exploitation, and Typed-State Gating in LLM Plan Evaluation","created":"2026-07-14","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":"2608.08722","title":"Gaming Without an Attacker: Benchmark Fingerprinting in LLM-Driven Search Under Selection Pressure","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2609.23083","title":"Directing large language models to follow the letter or spirit of the law","created":"2026-09-19","cited_by_count":0,"area":null}],"next_cursor":null}