{"total":174,"rows":[{"id":"2312.11456","title":"Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint","created":"2023-12-18","cited_by_count":350,"area":"alignment"},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"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":"2404.11999","title":"Token-level Direct Preference Optimization","created":"2024-04-18","cited_by_count":135,"area":"alignment"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2410.15553","title":"Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following","created":"2024-10-21","cited_by_count":102,"area":null},{"id":"2406.18853","title":"Decoding-Time Language Model Alignment with Multiple Objectives","created":"2024-06-27","cited_by_count":94,"area":"alignment"},{"id":"2501.05803","title":"Test-time Alignment of Diffusion Models without Reward Over-optimization","created":"2025-01-10","cited_by_count":93,"area":"diffusion"},{"id":"2403.08635","title":"Human Alignment of Large Language Models through Online Preference Optimisation","created":"2024-03-13","cited_by_count":91,"area":"alignment"},{"id":"2407.08639","title":"$\\beta$-DPO: Direct Preference Optimization with Dynamic $\\beta$","created":"2024-07-11","cited_by_count":90,"area":"alignment"},{"id":"2402.05369","title":"Noise Contrastive Alignment of Language Models with Explicit Rewards","created":"2024-02-08","cited_by_count":85,"area":"alignment"},{"id":"2407.13399","title":"Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization","created":"2024-07-18","cited_by_count":78,"area":"alignment"},{"id":"2405.16455","title":"On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization","created":"2024-05-26","cited_by_count":72,"area":"alignment"},{"id":"2507.08838","title":"wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models","created":"2025-07-07","cited_by_count":71,"area":"lr"},{"id":"2404.04626","title":"Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective","created":"2024-04-06","cited_by_count":69,"area":"alignment"},{"id":"2404.02657","title":"Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models","created":"2024-04-03","cited_by_count":65,"area":"lr"},{"id":"2406.09215","title":"On Softmax Direct Preference Optimization for Recommendation","created":"2024-06-13","cited_by_count":64,"area":"alignment"},{"id":"2404.07413","title":"JetMoE: Reaching Llama2 Performance with 0.1M Dollars","created":"2024-04-11","cited_by_count":57,"area":"moe"},{"id":"2404.09656","title":"Learn Your Reference Model for Real Good Alignment","created":"2024-04-15","cited_by_count":57,"area":"alignment"},{"id":"2407.07880","title":"Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization","created":"2024-07-10","cited_by_count":53,"area":"alignment"},{"id":"2402.07314","title":"Online Iterative Reinforcement Learning from Human Feedback with General Preference Model","created":"2024-02-11","cited_by_count":52,"area":"alignment"},{"id":"2501.18101","title":"Diverse Preference Optimization","created":"2025-01-30","cited_by_count":52,"area":"lr"},{"id":"2412.14516","title":"Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment","created":"2024-12-19","cited_by_count":51,"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":"2405.19107","title":"Offline Regularised Reinforcement Learning for Large Language Models Alignment","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2406.14563","title":"Model Merging and Safety Alignment: One Bad Model Spoils the Bunch","created":"2024-06-20","cited_by_count":43,"area":"alignment"},{"id":"2403.06279","title":"Fine-tuning of diffusion models via stochastic control: entropy regularization and beyond","created":"2024-03-10","cited_by_count":42,"area":"diffusion"},{"id":"2505.18116","title":"NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoning","created":"2025-05-23","cited_by_count":38,"area":"lr"},{"id":"2505.20065","title":"SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety","created":"2025-05-26","cited_by_count":37,"area":"alignment"},{"id":"2509.07430","title":"The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward","created":"2025-09-09","cited_by_count":37,"area":null},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2405.17346","title":"Prompt Optimization with Human Feedback","created":"2024-05-27","cited_by_count":35,"area":"alignment"},{"id":"2409.07253","title":"Alignment of Diffusion Models: Fundamentals, Challenges, and Future","created":"2024-09-11","cited_by_count":35,"area":"diffusion"},{"id":"2510.20817","title":"KL-Regularized Reinforcement Learning is Designed to Mode Collapse","created":"2025-10-23","cited_by_count":31,"area":"deeprl"},{"id":"2404.11049","title":"Stepwise Alignment for Constrained Language Model Policy Optimization","created":"2024-04-17","cited_by_count":30,"area":"alignment"},{"id":"2410.10148","title":"AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization","created":"2024-10-14","cited_by_count":29,"area":"alignment"},{"id":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28,"area":"lr"},{"id":"2403.01857","title":"Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences","created":"2024-03-04","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":"2506.17871","title":"LLM Probability Concentration: How Alignment Shrinks the Generative Horizon","created":"2025-06-22","cited_by_count":26,"area":"alignment"},{"id":"2504.16431","title":"Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion","created":"2025-04-23","cited_by_count":25,"area":"diffusion"},{"id":"2511.08594","title":"Diverse Preference Learning for Capabilities and Alignment","created":"2025-10-29","cited_by_count":25,"area":"alignment"},{"id":"2404.13846","title":"Filtered Direct Preference Optimization","created":"2024-04-22","cited_by_count":24,"area":"alignment"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2405.15065","title":"Direct Preference Optimization With Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences","created":"2024-05-23","cited_by_count":23,"area":"alignment"},{"id":"2406.05883","title":"Information Theoretic Guarantees For Policy Alignment In Large Language Models","created":"2024-06-09","cited_by_count":23,"area":"alignment"},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2406.01660","title":"Self-Improving Robust Preference Optimization","created":"2024-06-03","cited_by_count":19,"area":"alignment"},{"id":"2410.21662","title":"$f$-PO: Generalizing Preference Optimization with $f$-divergence Minimization","created":"2024-10-29","cited_by_count":19,"area":"alignment"},{"id":"2405.14953","title":"MallowsPO: Fine-Tune Your LLM with Preference Dispersions","created":"2024-05-23","cited_by_count":18,"area":"alignment"},{"id":"2409.06691","title":"Geometric-Averaged Preference Optimization for Soft Preference Labels","created":"2024-09-10","cited_by_count":18,"area":"alignment"},{"id":"2412.09243","title":"SPRec: Self-Play to Debias LLM-based Recommendation","created":"2024-12-12","cited_by_count":18,"area":"synth"},{"id":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17,"area":"alignment"},{"id":"2404.04102","title":"ROPO: Robust Preference Optimization for Large Language Models","created":"2024-04-05","cited_by_count":16,"area":"alignment"},{"id":"2410.12138","title":"Preference Optimization with Multi-Sample Comparisons","created":"2024-10-16","cited_by_count":16,"area":"diffusion"},{"id":"2502.14354","title":"Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment","created":"2025-02-20","cited_by_count":16,"area":"lr"},{"id":"2503.08942","title":"Extragradient Preference Optimization (EGPO): Beyond Last-Iterate Convergence for Nash Learning from Human Feedback","created":"2025-03-11","cited_by_count":16,"area":"alignment"},{"id":"2404.00530","title":"Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization","created":"2024-03-31","cited_by_count":15,"area":"alignment"},{"id":"2409.09774","title":"Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences through $f$-divergence Minimization","created":"2024-09-15","cited_by_count":15,"area":"alignment"},{"id":"2501.11463","title":"Curiosity-Driven Reinforcement Learning from Human Feedback","created":"2025-01-20","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":"2501.03884","title":"AlphaPO: Reward Shape Matters for LLM Alignment","created":"2025-01-07","cited_by_count":14,"area":"alignment"},{"id":"2505.19653","title":"Token-Importance Guided Direct Preference Optimization","created":"2025-05-26","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":"2504.03784","title":"Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning","created":"2025-04-03","cited_by_count":13,"area":"alignment"},{"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":"2403.12017","title":"Supervised Fine-Tuning as Inverse Reinforcement Learning","created":"2024-03-18","cited_by_count":12,"area":"alignment"},{"id":"2506.01183","title":"Doubly Robust Alignment for Large Language Models","created":"2025-06-01","cited_by_count":12,"area":"alignment"},{"id":"2410.02596","title":"Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks","created":"2024-10-03","cited_by_count":11,"area":null},{"id":"2411.12843","title":"Reward Modeling with Ordinal Feedback: Wisdom of the Crowd","created":"2024-11-19","cited_by_count":11,"area":"alignment"},{"id":"2502.01203","title":"KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity","created":"2025-02-03","cited_by_count":11,"area":"alignment"},{"id":"2502.15145","title":"Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF","created":"2025-02-21","cited_by_count":11,"area":"alignment"},{"id":"2507.00445","title":"Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular Design","created":"2025-07-01","cited_by_count":11,"area":"diffusion"},{"id":"2604.16027","title":"Where does output diversity collapse in post-training?","created":"2026-04-17","cited_by_count":11,"area":null},{"id":"2405.11647","title":"Hummer: Towards Limited Competitive Preference Dataset","created":"2024-05-19","cited_by_count":10,"area":"alignment"},{"id":"2409.05622","title":"Forward KL Regularized Preference Optimization for Aligning Diffusion Policies","created":"2024-09-09","cited_by_count":10,"area":"diffusion"},{"id":"2501.18537","title":"Loss Functions and Operators Generated by f-Divergences","created":"2025-01-30","cited_by_count":10,"area":null},{"id":"2505.19601","title":"Preference Optimization by Estimating the Ratio of the Data Distribution","created":"2025-05-26","cited_by_count":9,"area":"alignment"},{"id":"2506.04721","title":"SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combat","created":"2025-06-05","cited_by_count":9,"area":"alignment"},{"id":"2502.00602","title":"Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing","created":"2025-02-02","cited_by_count":8,"area":null},{"id":"2511.05650","title":"Optimizing Diversity and Quality through Base-Aligned Model Collaboration","created":"2025-11-07","cited_by_count":8,"area":null},{"id":"2512.15605","title":"Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction","created":"2025-12-17","cited_by_count":8,"area":null},{"id":"2405.21040","title":"Direct Alignment of Language Models via Quality-Aware Self-Refinement","created":"2024-05-31","cited_by_count":7,"area":"alignment"},{"id":"2505.08507","title":"InfoPO: On Mutual Information Maximization for Large Language Model Alignment","created":"2025-05-13","cited_by_count":7,"area":"alignment"},{"id":"2508.09654","title":"Improving Diversity in Language Models: When Temperature Fails, Change the Loss","created":"2025-08-13","cited_by_count":7,"area":null},{"id":"2509.23102","title":"Multiplayer Nash Preference Optimization","created":"2025-09-27","cited_by_count":7,"area":"alignment"},{"id":"2510.03865","title":"Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning Exploration","created":"2025-10-04","cited_by_count":7,"area":"lr"},{"id":"2605.03327","title":"DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignment","created":"2026-05-05","cited_by_count":7,"area":"lr"},{"id":"2409.10825","title":"Unveiling and Mitigating Bias in Large Language Model Recommendations: A Path to Fairness","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2503.20105","title":"Direct Post-Training Preference Alignment for Multi-Agent Motion Generation Models Using Implicit Feedback from Pre-training Demonstrations","created":"2025-03-25","cited_by_count":6,"area":"agents"},{"id":"2506.07459","title":"ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning","created":"2025-06-09","cited_by_count":6,"area":"deeprl"},{"id":"2506.07492","title":"Explicit Preference Optimization: No Need for an Implicit Reward Model","created":"2025-06-09","cited_by_count":6,"area":"alignment"},{"id":"2509.12434","title":"Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization","created":"2025-09-15","cited_by_count":6,"area":"lr"},{"id":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","cited_by_count":6,"area":"lr"},{"id":"2407.09072","title":"New Desiderata for Direct Preference Optimization","created":"2024-07-12","cited_by_count":5,"area":"alignment"},{"id":"2409.14836","title":"Orthogonal Finetuning for Direct Preference Optimization","created":"2024-09-23","cited_by_count":5,"area":"alignment"},{"id":"2410.19471","title":"Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimization","created":"2024-10-25","cited_by_count":5,"area":null},{"id":"2412.14050","title":"Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2503.00030","title":"RSPO: Regularized Self-Play Alignment of Large Language Models","created":"2025-02-24","cited_by_count":5,"area":"alignment"},{"id":"2505.23316","title":"Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO","created":"2025-05-29","cited_by_count":5,"area":"alignment"}],"next_cursor":"100"}