{"total":66,"rows":[{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912,"area":"alignment"},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055,"area":"alignment"},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571,"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":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247,"area":"alignment"},{"id":"1806.01946","title":"Learning to Understand Goal Specifications by Modelling Reward","created":"2018-06-05","cited_by_count":80,"area":"alignment"},{"id":"2005.02575","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","created":"2020-05-06","cited_by_count":71,"area":"alignment"},{"id":"2305.15363","title":"Inverse Preference Learning: Preference-based RL without a Reward Function","created":"2023-05-24","cited_by_count":68,"area":"alignment"},{"id":"2603.02115","title":"Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons","created":"2026-03-02","cited_by_count":60,"area":"alignment"},{"id":"2403.03185","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","created":"2024-03-05","cited_by_count":50,"area":"alignment"},{"id":"2308.02585","title":"PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback","created":"2023-08-03","cited_by_count":40,"area":"alignment"},{"id":"1911.00459","title":"Positive-Unlabeled Reward Learning","created":"2019-11-01","cited_by_count":37,"area":"alignment"},{"id":"2312.10584","title":"Policy Optimization in RLHF: The Impact of Out-of-preference Data","created":"2023-12-17","cited_by_count":35,"area":"alignment"},{"id":"2406.00888","title":"Aligning Language Models with Demonstrated Feedback","created":"2024-06-02","cited_by_count":34,"area":"alignment"},{"id":"2602.19313","title":"TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics","created":"2026-02-22","cited_by_count":33,"area":"alignment"},{"id":"2410.14660","title":"A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learning","created":"2024-10-18","cited_by_count":30,"area":"alignment"},{"id":"2311.08045","title":"Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game","created":"2023-11-14","cited_by_count":27,"area":"alignment"},{"id":"2405.15624","title":"Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning","created":"2024-05-24","cited_by_count":27,"area":"alignment"},{"id":"2012.06899","title":"Semi-supervised reward learning for offline reinforcement learning","created":"2020-12-12","cited_by_count":23,"area":"alignment"},{"id":"2310.01045","title":"Tool-Augmented Reward Modeling","created":"2023-10-02","cited_by_count":20,"area":"alignment"},{"id":"2310.06147","title":"Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond","created":"2023-10-09","cited_by_count":20,"area":"alignment"},{"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":"2504.06141","title":"Adversarial Training of Reward Models","created":"2025-04-08","cited_by_count":18,"area":"alignment"},{"id":"2507.00018","title":"Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections","created":"2025-06-15","cited_by_count":17,"area":"alignment"},{"id":"2406.04274","title":"Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models","created":"2024-06-06","cited_by_count":16,"area":"alignment"},{"id":"2507.05197","title":"Pre-Trained Policy Discriminators are General Reward Models","created":"2025-07-07","cited_by_count":15,"area":"alignment"},{"id":"2410.10093","title":"How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective","created":"2024-10-14","cited_by_count":14,"area":"alignment"},{"id":"2503.05079","title":"On a Connection Between Imitation Learning and RLHF","created":"2025-03-07","cited_by_count":13,"area":"alignment"},{"id":"2403.12017","title":"Supervised Fine-Tuning as Inverse Reinforcement Learning","created":"2024-03-18","cited_by_count":12,"area":"alignment"},{"id":"2408.12112","title":"Balancing Act: Prioritization Strategies for LLM-Designed Restless Bandit Rewards","created":"2024-08-22","cited_by_count":9,"area":"alignment"},{"id":"2410.10062","title":"Dreaming to Assist: Learning to Align with Human Objectives for Shared Control in High-Speed Racing","created":"2024-10-14","cited_by_count":7,"area":"alignment"},{"id":"2502.01616","title":"Preference VLM: Leveraging VLMs for Scalable Preference-Based Reinforcement Learning","created":"2025-02-03","cited_by_count":7,"area":"alignment"},{"id":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2608.09853","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","created":"2026-08-10","cited_by_count":7,"area":"alignment"},{"id":"2104.04748","title":"Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog Management","created":"2021-04-10","cited_by_count":6,"area":"alignment"},{"id":"2311.10284","title":"From \"Thumbs Up\" to \"10 out of 10\": Reconsidering Scalar Feedback in Interactive Reinforcement Learning","created":"2023-11-17","cited_by_count":6,"area":"alignment"},{"id":"2204.07123","title":"Retrospective on the 2021 BASALT Competition on Learning from Human Feedback","created":"2022-04-14","cited_by_count":5,"area":"alignment"},{"id":"2312.01957","title":"Distilled Self-Critique of LLMs with Synthetic Data: a Bayesian Perspective","created":"2023-12-04","cited_by_count":5,"area":"alignment"},{"id":"2506.22578","title":"The Hidden Link Between RLHF and Contrastive Learning","created":"2025-06-27","cited_by_count":5,"area":"alignment"},{"id":"2503.13538","title":"From Demonstrations to Rewards: Alignment Without Explicit Human Preferences","created":"2025-03-15","cited_by_count":4,"area":"alignment"},{"id":"2112.03482","title":"Combining Learning from Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in Minecraft","created":"2021-12-07","cited_by_count":3,"area":"alignment"},{"id":"2405.00578","title":"The Real, the Better: Aligning Large Language Models with Online Human Behaviors","created":"2024-05-01","cited_by_count":3,"area":"alignment"},{"id":"2405.07004","title":"Stealthy Imitation: Reward-guided Environment-free Policy Stealing","created":"2024-05-11","cited_by_count":3,"area":"alignment"},{"id":"2410.05782","title":"Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards","created":"2024-10-08","cited_by_count":3,"area":"alignment"},{"id":"2511.17879","title":"Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction","created":"2025-11-22","cited_by_count":3,"area":"alignment"},{"id":"2606.22027","title":"RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation","created":"2026-06-20","cited_by_count":3,"area":"alignment"},{"id":"2405.19763","title":"Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding","created":"2024-05-30","cited_by_count":2,"area":"alignment"},{"id":"2407.06459","title":"How Much Progress Did I Make? An Unexplored Human Feedback Signal for Teaching Robots","created":"2024-07-08","cited_by_count":2,"area":"alignment"},{"id":"2407.10839","title":"Offline Reinforcement Learning with Imputed Rewards","created":"2024-07-15","cited_by_count":2,"area":"alignment"},{"id":"2509.17116","title":"MCTS-EP: Empowering Embodied Planning with Online Preference Optimization","created":"2025-09-21","cited_by_count":2,"area":"alignment"},{"id":"2603.04861","title":"Causally Robust Reward Learning from Reason-Augmented Preference Feedback","created":"2026-03-05","cited_by_count":2,"area":"alignment"},{"id":"2509.22807","title":"MTRec: Learning to Align with User Preferences via Mental Reward Models","created":"2025-09-26","cited_by_count":1,"area":"alignment"},{"id":"2510.02493","title":"Beyond Imitation: Recovering Dense Rewards from Demonstrations","created":"2025-10-02","cited_by_count":1,"area":"alignment"},{"id":"2510.21090","title":"Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only","created":"2025-10-24","cited_by_count":1,"area":"alignment"},{"id":"2606.00083","title":"From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models","created":"2026-05-22","cited_by_count":1,"area":"alignment"},{"id":"2607.24900","title":"Inverse RL Helps Align AI by Imitating Humans","created":"2026-07-27","cited_by_count":1,"area":"alignment"},{"id":"2503.04679","title":"Multi-Agent Inverse Q-Learning from Demonstrations","created":"2025-03-06","cited_by_count":0,"area":"alignment"},{"id":"2510.02180","title":"GRACE: A Language Model Framework for Explainable Inverse Reinforcement Learning","created":"2025-10-02","cited_by_count":0,"area":"alignment"},{"id":"2510.15728","title":"RLAF: Reinforcement Learning from Automaton Feedback","created":"2025-10-17","cited_by_count":0,"area":"alignment"},{"id":"2602.18582","title":"Hierarchical Reward Design from Language: Enhancing Alignment of Agent Behavior with Human Specifications","created":"2026-02-20","cited_by_count":0,"area":"alignment"},{"id":"2603.07784","title":"ProgAgent:A Continual RL Agent with Progress-Aware Rewards","created":"2026-03-08","cited_by_count":0,"area":"alignment"},{"id":"2605.20654","title":"REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak","created":"2026-05-20","cited_by_count":0,"area":"alignment"},{"id":"2607.01897","title":"Rank-Then-Act: Reward-Free Control from Frame-Order Progress","created":"2026-07-02","cited_by_count":0,"area":"alignment"},{"id":"2608.06105","title":"Does Latent Context Help? A Controlled Evaluation of Inverse Reinforcement Learning in Arctic Shipping","created":"2026-08-06","cited_by_count":0,"area":"alignment"},{"id":"2609.04066","title":"Subspace Inference Enables Efficient Active Reward Learning from Preferences","created":"2026-09-03","cited_by_count":0,"area":"alignment"}],"next_cursor":null}