{"total":256,"rows":[{"id":"2310.11564","title":"Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging","created":"2023-10-17","cited_by_count":280,"area":"alignment"},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184,"area":"alignment"},{"id":"2402.10207","title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment","created":"2024-02-15","cited_by_count":175,"area":"alignment"},{"id":"2402.07510","title":"Secret Collusion among AI Agents: Multi-Agent Deception via Steganography","created":"2024-02-12","cited_by_count":113,"area":"agents"},{"id":"2210.12765","title":"Multi-Objective GFlowNets","created":"2022-10-23","cited_by_count":101,"area":null},{"id":"2208.07914","title":"PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm","created":"2022-08-16","cited_by_count":58,"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":"2405.06639","title":"Value Augmented Sampling for Language Model Alignment and Personalization","created":"2024-05-10","cited_by_count":49,"area":"alignment"},{"id":"2301.07784","title":"Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization","created":"2023-01-18","cited_by_count":48,"area":null},{"id":"2407.15762","title":"Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning","created":"2024-07-22","cited_by_count":43,"area":null},{"id":"2305.00567","title":"Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL","created":"2023-04-30","cited_by_count":36,"area":null},{"id":"2311.12495","title":"Multi-Objective Reinforcement Learning Based on Decomposition: A Taxonomy and Framework","created":"2023-11-21","cited_by_count":31,"area":null},{"id":"2312.09337","title":"Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences","created":"2023-12-14","cited_by_count":26,"area":"alignment"},{"id":"2204.05036","title":"Pareto Conditioned Networks","created":"2022-04-11","cited_by_count":25,"area":null},{"id":"2108.09003","title":"Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey","created":"2021-08-20","cited_by_count":24,"area":null},{"id":"2509.11452","title":"Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting","created":"2025-09-14","cited_by_count":23,"area":"alignment"},{"id":"2509.22047","title":"MO-GRPO: Mitigating Reward Hacking of Group Relative Policy Optimization on Multi-Objective Problems","created":"2025-09-26","cited_by_count":23,"area":"lr"},{"id":"2206.11326","title":"Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer","created":"2022-06-22","cited_by_count":22,"area":null},{"id":"2209.12351","title":"Deep Reinforcement Learning for Adaptive Mesh Refinement","created":"2022-09-25","cited_by_count":20,"area":null},{"id":"2501.06773","title":"Pareto Set Learning for Multi-Objective Reinforcement Learning","created":"2025-01-12","cited_by_count":20,"area":"deeprl"},{"id":"2409.00328","title":"Foundations of Multivariate Distributional Reinforcement Learning","created":"2024-08-31","cited_by_count":17,"area":"deeprl"},{"id":"2402.11711","title":"MORL-Prompt: An Empirical Analysis of Multi-Objective Reinforcement Learning for Discrete Prompt Optimization","created":"2024-02-18","cited_by_count":16,"area":"alignment"},{"id":"2405.19650","title":"Few for Many: Tchebycheff Set Scalarization for Many-Objective Optimization","created":"2024-05-30","cited_by_count":16,"area":null},{"id":"2406.07826","title":"The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm","created":"2024-06-12","cited_by_count":15,"area":"deeprl"},{"id":"2207.03270","title":"gym-DSSAT: a crop model turned into a Reinforcement Learning environment","created":"2022-07-07","cited_by_count":13,"area":null},{"id":"2409.15755","title":"Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach","created":"2024-09-24","cited_by_count":13,"area":"deeprl"},{"id":"2505.10892","title":"Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models","created":"2025-05-16","cited_by_count":13,"area":"alignment"},{"id":"2110.12311","title":"Vector Optimization with Stochastic Bandit Feedback","created":"2021-10-23","cited_by_count":12,"area":null},{"id":"2602.02495","title":"Reward-free Alignment for Conflicting Objectives","created":"2026-02-02","cited_by_count":11,"area":"alignment"},{"id":"2312.11337","title":"Challenges for Reinforcement Learning in Quantum Circuit Design","created":"2023-12-18","cited_by_count":9,"area":null},{"id":"2505.23708","title":"AMOR: Adaptive Character Control through Multi-Objective Reinforcement Learning","created":"2025-05-29","cited_by_count":9,"area":"deeprl"},{"id":"2411.03651","title":"Policy Aggregation","created":"2024-11-06","cited_by_count":8,"area":null},{"id":"2503.00799","title":"On Generalization Across Environments In Multi-Objective Reinforcement Learning","created":"2025-03-02","cited_by_count":8,"area":"deeprl"},{"id":"2605.11882","title":"On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment","created":"2026-05-12","cited_by_count":8,"area":"agents"},{"id":"2605.22817","title":"Vector Policy Optimization: Training for Diversity Improves Test-Time Search","created":"2026-05-21","cited_by_count":8,"area":null},{"id":"2302.03805","title":"Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback","created":"2023-02-07","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":"2507.14066","title":"Preference-based Multi-Objective Reinforcement Learning","created":"2025-07-18","cited_by_count":7,"area":"deeprl"},{"id":"2512.04784","title":"PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling","created":"2025-12-02","cited_by_count":7,"area":"alignment"},{"id":"2106.01048","title":"Expected Scalarised Returns Dominance: A New Solution Concept for Multi-Objective Decision Making","created":"2021-06-02","cited_by_count":6,"area":null},{"id":"2206.13901","title":"Value Function Decomposition for Iterative Design of Reinforcement Learning Agents","created":"2022-06-24","cited_by_count":6,"area":null},{"id":"2306.03293","title":"Towards Fairness in Personalized Ads Using Impression Variance Aware Reinforcement Learning","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2407.16312","title":"MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning","created":"2024-07-23","cited_by_count":6,"area":null},{"id":"2410.23630","title":"Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2412.01566","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","created":"2024-12-02","cited_by_count":6,"area":null},{"id":"2504.20106","title":"Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors","created":"2025-04-27","cited_by_count":6,"area":"alignment"},{"id":"2211.00801","title":"Multi-Agent Reinforcement Learning for Adaptive Mesh Refinement","created":"2022-11-02","cited_by_count":5,"area":null},{"id":"2211.13032","title":"Monte Carlo Tree Search Algorithms for Risk-Aware and Multi-Objective Reinforcement Learning","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2302.00586","title":"PRUDEX-Compass: Towards Systematic Evaluation of Reinforcement Learning in Financial Markets","created":"2023-01-14","cited_by_count":5,"area":"moe"},{"id":"2310.02360","title":"Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning","created":"2023-10-03","cited_by_count":5,"area":null},{"id":"2311.11288","title":"What Lies beyond the Pareto Front? A Survey on Decision-Support Methods for Multi-Objective Optimization","created":"2023-11-19","cited_by_count":5,"area":null},{"id":"2403.00282","title":"Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning","created":"2024-03-01","cited_by_count":5,"area":"deeprl"},{"id":"2403.17164","title":"Multi-Objective Quality-Diversity for Crystal Structure Prediction","created":"2024-03-25","cited_by_count":5,"area":null},{"id":"2412.10961","title":"PSMGD: Periodic Stochastic Multi-Gradient Descent for Fast Multi-Objective Optimization","created":"2024-12-14","cited_by_count":5,"area":"deeprl"},{"id":"2509.01765","title":"Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control","created":"2025-09-01","cited_by_count":5,"area":"deeprl"},{"id":"2510.20235","title":"Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach","created":"2025-10-23","cited_by_count":5,"area":"deeprl"},{"id":"2202.12174","title":"Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?","created":"2022-02-24","cited_by_count":4,"area":null},{"id":"2312.09126","title":"Towards Trustworthy AI Software Development Assistance","created":"2023-12-14","cited_by_count":4,"area":null},{"id":"2401.02160","title":"Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning","created":"2024-01-04","cited_by_count":4,"area":"deeprl"},{"id":"2401.06514","title":"Personalized Reinforcement Learning with a Budget of Policies","created":"2024-01-12","cited_by_count":4,"area":"deeprl"},{"id":"2407.04181","title":"Orchestrating LLMs with Different Personalizations","created":"2024-07-04","cited_by_count":4,"area":"alignment"},{"id":"2408.15501","title":"MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement Learning","created":"2024-08-28","cited_by_count":4,"area":"diffusion"},{"id":"2409.02428","title":"Language Models as Efficient Reward Function Searchers for Custom-Environment Multi-Objective Reinforcement","created":"2024-09-04","cited_by_count":4,"area":"alignment"},{"id":"2410.02236","title":"C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front","created":"2024-10-03","cited_by_count":4,"area":"deeprl"},{"id":"2410.11221","title":"Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2411.18195","title":"Scalable Multi-Objective Reinforcement Learning with Fairness Guarantees using Lorenz Dominance","created":"2024-11-27","cited_by_count":4,"area":"deeprl"},{"id":"2503.00527","title":"Never too Prim to Swim: An LLM-Enhanced RL-based Adaptive S-Surface Controller for AUVs under Extreme Sea Conditions","created":"2025-03-01","cited_by_count":4,"area":null},{"id":"2505.02579","title":"EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning","created":"2025-05-05","cited_by_count":4,"area":null},{"id":"2506.06981","title":"Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments","created":"2025-06-08","cited_by_count":4,"area":"deeprl"},{"id":"2510.03544","title":"Agile Tradespace Exploration for Space Rendezvous Mission Design via Transformers","created":"2025-10-03","cited_by_count":4,"area":null},{"id":"2207.00368","title":"Multi-Objective Coordination Graphs for the Expected Scalarised Returns with Generative Flow Models","created":"2022-07-01","cited_by_count":3,"area":null},{"id":"2207.11386","title":"Learning an Adaptive Forwarding Strategy for Mobile Wireless Networks: Resource Usage vs. Latency","created":"2022-07-23","cited_by_count":3,"area":null},{"id":"2302.05257","title":"Piecewise-Stationary Multi-Objective Multi-Armed Bandit with Application to Joint Communications and Sensing","created":"2023-02-10","cited_by_count":3,"area":null},{"id":"2304.14115","title":"Inferring Preferences from Demonstrations in Multi-objective Reinforcement Learning: A Dynamic Weight-based Approach","created":"2023-04-27","cited_by_count":3,"area":null},{"id":"2308.06935","title":"Insurance pricing on price comparison websites via reinforcement learning","created":"2023-08-14","cited_by_count":3,"area":null},{"id":"2310.16487","title":"Hyperparameter Optimization for Multi-Objective Reinforcement Learning","created":"2023-10-25","cited_by_count":3,"area":null},{"id":"2409.19617","title":"LiRA: Light-Robust Adversary for Model-based Reinforcement Learning in Real World","created":"2024-09-29","cited_by_count":3,"area":"deeprl"},{"id":"2501.04982","title":"CuRLA: Curriculum Learning Based Deep Reinforcement Learning for Autonomous Driving","created":"2025-01-09","cited_by_count":3,"area":"driving"},{"id":"2502.05633","title":"Mol-MoE: Training Preference-Guided Routers for Molecule Generation","created":"2025-02-08","cited_by_count":3,"area":"moe"},{"id":"2505.05223","title":"Multi-Objective Reinforcement Learning for Adaptable Personalized Autonomous Driving","created":"2025-05-08","cited_by_count":3,"area":"driving"},{"id":"2605.05750","title":"RVPO: Risk-Sensitive Alignment via Variance Regularization","created":"2026-05-07","cited_by_count":3,"area":"alignment"},{"id":"2203.04579","title":"Multi-Objective reward generalization: Improving performance of Deep Reinforcement Learning for applications in single-asset trading","created":"2022-03-09","cited_by_count":2,"area":null},{"id":"2211.01036","title":"Explainable AI over the Internet of Things (IoT): Overview, State-of-the-Art and Future Directions","created":"2022-11-02","cited_by_count":2,"area":null},{"id":"2302.12668","title":"Improving the Data Efficiency of Multi-Objective Quality-Diversity through Gradient Assistance and Crowding Exploration","created":"2023-02-24","cited_by_count":2,"area":null},{"id":"2305.05560","title":"Distributional Multi-Objective Decision Making","created":"2023-05-09","cited_by_count":2,"area":null},{"id":"2306.08044","title":"Pruning the Way to Reliable Policies: A Multi-Objective Deep Q-Learning Approach to Critical Care","created":"2023-06-13","cited_by_count":2,"area":null},{"id":"2310.18617","title":"Pessimistic Off-Policy Multi-Objective Optimization","created":"2023-10-28","cited_by_count":2,"area":null},{"id":"2401.03163","title":"An Empirical Investigation of Value-Based Multi-objective Reinforcement Learning for Stochastic Environments","created":"2024-01-06","cited_by_count":2,"area":"deeprl"},{"id":"2401.07722","title":"Inferring Preferences from Demonstrations in Multi-Objective Residential Energy Management","created":"2024-01-15","cited_by_count":2,"area":null},{"id":"2402.13785","title":"Composing Reinforcement Learning Policies, with Formal Guarantees","created":"2024-02-21","cited_by_count":2,"area":"deeprl"},{"id":"2403.13729","title":"Reinforcement Learning for Online Testing of Autonomous Driving Systems: a Replication and Extension Study","created":"2024-03-20","cited_by_count":2,"area":"driving"},{"id":"2404.03997","title":"Demonstration Guided Multi-Objective Reinforcement Learning","created":"2024-04-05","cited_by_count":2,"area":"deeprl"},{"id":"2404.04857","title":"Demonstration-Enhanced Adaptable Multi-Objective Robot Navigation","created":"2024-04-07","cited_by_count":2,"area":"deeprl"},{"id":"2406.04516","title":"Online Joint Fine-tuning of Multi-Agent Flows","created":"2024-06-06","cited_by_count":2,"area":"agents"},{"id":"2406.08440","title":"Adaptive Swarm Mesh Refinement using Deep Reinforcement Learning with Local Rewards","created":"2024-06-12","cited_by_count":2,"area":"deeprl"},{"id":"2407.00805","title":"Towards Shutdownable Agents via Stochastic Choice","created":"2024-06-30","cited_by_count":2,"area":null},{"id":"2407.11489","title":"A Meta-Learning Approach for Multi-Objective Reinforcement Learning in Sustainable Home Environments","created":"2024-07-16","cited_by_count":2,"area":"deeprl"},{"id":"2407.18597","title":"Reinforcement Learning for Sustainable Energy: A Survey","created":"2024-07-26","cited_by_count":2,"area":"deeprl"},{"id":"2410.10377","title":"Learning Sub-Second Routing Optimization in Computer Networks requires Packet-Level Dynamics","created":"2024-10-14","cited_by_count":2,"area":"deeprl"}],"next_cursor":"100"}