{"total":92,"rows":[{"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":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2410.03642","title":"Aligning LLMs with Individual Preferences via Interaction","created":"2024-10-04","cited_by_count":63,"area":"alignment"},{"id":"2502.16923","title":"A Systematic Survey of Automatic Prompt Optimization Techniques","created":"2025-02-24","cited_by_count":63,"area":null},{"id":"2410.09893","title":"RMB: Comprehensively Benchmarking Reward Models in LLM Alignment","created":"2024-10-13","cited_by_count":61,"area":"alignment"},{"id":"2502.19301","title":"Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond","created":"2025-02-26","cited_by_count":61,"area":"lr"},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"id":"2408.06266","title":"Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment","created":"2024-08-12","cited_by_count":46,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2504.04158","title":"JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration","created":"2025-04-05","cited_by_count":34,"area":"driving"},{"id":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25,"area":"lr"},{"id":"2503.11441","title":"D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning","created":"2025-03-14","cited_by_count":21,"area":null},{"id":"2410.04203","title":"RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization","created":"2024-10-05","cited_by_count":19,"area":"alignment"},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2505.15710","title":"Advancing LLM Safe Alignment with Safety Representation Ranking","created":"2025-05-21","cited_by_count":16,"area":"safety"},{"id":"2508.17608","title":"ChartMaster: Advancing Chart-to-Code Generation with Real-World Charts and Chart Similarity Reinforcement Learning","created":"2025-08-25","cited_by_count":16,"area":null},{"id":"2505.02666","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","created":"2025-05-05","cited_by_count":15,"area":"alignment"},{"id":"2410.10862","title":"Superficial Safety Alignment Hypothesis","created":"2024-10-07","cited_by_count":14,"area":"alignment"},{"id":"2502.11401","title":"Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment","created":"2025-02-17","cited_by_count":14,"area":null},{"id":"2506.22200","title":"EFRame: Deeper Reasoning via Exploration-Filter-Replay Reinforcement Learning Framework","created":"2025-06-27","cited_by_count":14,"area":"lr"},{"id":"2505.17646","title":"Unveiling the Basin-Like Loss Landscape in Large Language Models","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2505.19056","title":"An Embarrassingly Simple Defense Against LLM Abliteration Attacks","created":"2025-05-25","cited_by_count":13,"area":"safety"},{"id":"2506.02698","title":"Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences","created":"2025-06-03","cited_by_count":13,"area":"diffusion"},{"id":"2502.11541","title":"MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training","created":"2025-02-17","cited_by_count":12,"area":null},{"id":"2502.19557","title":"Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?","created":"2025-02-26","cited_by_count":12,"area":"lr"},{"id":"2502.00203","title":"Reward-aware Preference Optimization: A Unified Mathematical Framework for Model Alignment","created":"2025-01-31","cited_by_count":10,"area":"lr"},{"id":"2504.20468","title":"Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception","created":"2025-04-29","cited_by_count":10,"area":"mllm"},{"id":"2505.12186","title":"Self-Destructive Language Model","created":"2025-05-18","cited_by_count":10,"area":"safety"},{"id":"2509.21761","title":"Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models","created":"2025-09-26","cited_by_count":10,"area":"safety"},{"id":"2505.17072","title":"Safety Alignment Can Be Not Superficial With Explicit Safety Signals","created":"2025-05-19","cited_by_count":9,"area":"alignment"},{"id":"2506.08686","title":"Brevity is the soul of sustainability: Characterizing LLM response lengths","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2510.13285","title":"In-Distribution Steering: Balancing Control and Coherence in Language Model Generation","created":"2025-10-15","cited_by_count":9,"area":"mechinterp"},{"id":"2512.13655","title":"Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation","created":"2025-12-15","cited_by_count":9,"area":"alignment"},{"id":"2503.01642","title":"Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning","created":"2025-03-03","cited_by_count":8,"area":"lr"},{"id":"2504.01735","title":"AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization","created":"2025-04-02","cited_by_count":8,"area":"mllm"},{"id":"2505.15694","title":"A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO","created":"2025-05-21","cited_by_count":8,"area":"alignment"},{"id":"2408.07471","title":"Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization","created":"2024-08-14","cited_by_count":7,"area":"alignment"},{"id":"2505.00038","title":"HyPerAlign: Interpretable Personalized LLM Alignment via Hypothesis Generation","created":"2025-04-29","cited_by_count":7,"area":"alignment"},{"id":"2505.15753","title":"Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval","created":"2025-05-21","cited_by_count":7,"area":"safety"},{"id":"2506.08967","title":"Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model","created":"2025-06-10","cited_by_count":7,"area":null},{"id":"2512.00601","title":"Clinical-R1: Empowering Large Language Models for Faithful and Comprehensive Reasoning with Clinical Objective Relative Policy Optimization","created":"2025-11-29","cited_by_count":7,"area":"lr"},{"id":"2411.10912","title":"SPICA: Retrieving Scenarios for Pluralistic In-Context Alignment","created":"2024-11-16","cited_by_count":6,"area":"alignment"},{"id":"2601.08421","title":"Coverage Improvement and Fast Convergence of On-policy Preference Learning","created":"2026-01-13","cited_by_count":6,"area":"alignment"},{"id":"2410.08316","title":"COS-DPO: Conditioned One-Shot Multi-Objective Fine-Tuning Framework","created":"2024-10-10","cited_by_count":5,"area":"alignment"},{"id":"2511.17579","title":"Multi-Value Alignment for LLMs via Value Decorrelation and Extrapolation","created":"2025-11-15","cited_by_count":5,"area":"alignment"},{"id":"2505.00031","title":"Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving","created":"2025-04-28","cited_by_count":4,"area":"synth"},{"id":"2509.16444","title":"Domain-Specific Constitutional AI: Enhancing Safety in LLM-Powered Mental Health Chatbots","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2510.02850","title":"Reward Model Routing in Alignment","created":"2025-10-03","cited_by_count":4,"area":"alignment"},{"id":"2510.13212","title":"Towards Understanding Valuable Preference Data for Large Language Model Alignment","created":"2025-10-15","cited_by_count":4,"area":"alignment"},{"id":"2603.23268","title":"SafeSeek: Universal Attribution of Safety Circuits in Language Models","created":"2026-03-24","cited_by_count":4,"area":"safety"},{"id":"2505.21784","title":"Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation","created":"2025-05-27","cited_by_count":3,"area":"lr"},{"id":"2508.02823","title":"NeuroSync: Intent-Aware Code-Based Problem Solving via Direct LLM Understanding Modification","created":"2025-08-05","cited_by_count":3,"area":null},{"id":"2510.16449","title":"TrajSelector: Harnessing Latent Representations for Efficient and Effective Best-of-N in Large Reasoning Model","created":"2025-10-18","cited_by_count":3,"area":"lr"},{"id":"2510.21190","title":"The Trojan Example: Jailbreaking LLMs through Template Filling and Unsafety Reasoning","created":"2025-10-24","cited_by_count":3,"area":"alignment"},{"id":"2409.07268","title":"Multi-Type Preference Learning: Empowering Preference-Based Reinforcement Learning with Equal Preferences","created":"2024-09-11","cited_by_count":2,"area":"deeprl"},{"id":"2503.04789","title":"Aligning Extraction and Generation for Robust Retrieval-Augmented Generation","created":"2025-02-28","cited_by_count":2,"area":"rag"},{"id":"2505.21191","title":"Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities","created":"2025-05-27","cited_by_count":2,"area":"moe"},{"id":"2506.07276","title":"Tokenized Bandit for LLM Decoding and Alignment","created":"2025-06-08","cited_by_count":2,"area":null},{"id":"2508.09016","title":"A Survey on Training-free Alignment of Large Language Models","created":"2025-08-12","cited_by_count":2,"area":"alignment"},{"id":"2602.08905","title":"Efficient and Stable Reinforcement Learning for Diffusion Language Models","created":"2026-02-09","cited_by_count":2,"area":"lr"},{"id":"2602.16977","title":"Fail-Closed Alignment for Large Language Models","created":"2026-02-19","cited_by_count":2,"area":"alignment"},{"id":"2603.23279","title":"Emergence of Fragility in LLM-based Social Networks: the Case of Moltbook","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2502.12066","title":"CONSTRUCTA: Automating Commercial Construction Schedules in Fabrication Facilities with Large Language Models","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2505.09576","title":"Ethics and Persuasion in Reinforcement Learning from Human Feedback: A Procedural Rhetorical Approach","created":"2025-05-14","cited_by_count":1,"area":"alignment"},{"id":"2507.06528","title":"InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes under Herd Behavior","created":"2025-07-09","cited_by_count":1,"area":"alignment"},{"id":"2507.22326","title":"An Explainable Emotion Alignment Framework for LLM-Empowered Agent in Metaverse Service Ecosystem","created":"2025-07-30","cited_by_count":1,"area":"agents"},{"id":"2509.20680","title":"Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2511.12796","title":"Maximizing the efficiency of human feedback in AI alignment: a comparative analysis","created":"2025-11-16","cited_by_count":1,"area":"alignment"},{"id":"2601.05578","title":"Reinforcement Learning of Large Language Models for Interpretable Credit Card Fraud Detection","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2601.10416","title":"LLMdoctor: Token-Level Flow-Guided Preference Optimization for Efficient Test-Time Alignment of Large Language Models","created":"2026-01-15","cited_by_count":1,"area":"alignment"},{"id":"2601.12730","title":"Distribution-Centric Policy Optimization Dominates Exploration-Exploitation Trade-off","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2603.14126","title":"The Institutional Scaling Law: Non-Monotonic Fitness, Capability-Trust Divergence, and Symbiogenetic Scaling in Generative AI","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2604.27859","title":"Rethinking Agentic Reinforcement Learning In Large Language Models","created":"2026-04-30","cited_by_count":1,"area":"lr"},{"id":"2606.16733","title":"A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"id":"2410.22151","title":"Standardization Trends on Safety and Trustworthiness Technology for Advanced AI","created":"2024-10-29","cited_by_count":0,"area":"lr"},{"id":"2502.19347","title":"Controlled Diversity: Length-optimized Natural Language Generation","created":"2025-02-26","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":"2511.06682","title":"Textual Self-attention Network: Test-Time Preference Optimization through Textual Gradient-based Attention","created":"2025-11-10","cited_by_count":0,"area":"alignment"},{"id":"2511.11667","title":"Beyond Superficial Forgetting: Thorough Unlearning through Knowledge Density Estimation and Block Re-insertion","created":"2025-11-11","cited_by_count":0,"area":"safety"},{"id":"2511.12782","title":"LLM Reinforcement in Context","created":"2025-11-16","cited_by_count":0,"area":"alignment"},{"id":"2511.18933","title":"Defending Large Language Models Against Jailbreak Exploits with Responsible AI Considerations","created":"2025-11-24","cited_by_count":0,"area":"safety"},{"id":"2512.03001","title":"Invasive Context Engineering to Control Large Language Models","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2601.03005","title":"JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification","created":"2026-01-06","cited_by_count":0,"area":"alignment"},{"id":"2601.03451","title":"Microeconomic Foundations of Multi-Agent Learning","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.04563","title":"A Vision for Multisensory Intelligence: Sensing, Science, and Synergy","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2601.06157","title":"ECLIPTICA -- A Framework for Switchable LLM Alignment via CITA - Contrastive Instruction-Tuned Alignment","created":"2026-01-06","cited_by_count":0,"area":"alignment"},{"id":"2601.13122","title":"Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2602.02027","title":"Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron","created":"2026-02-02","cited_by_count":0,"area":"safety"},{"id":"2602.06836","title":"LLM Active Alignment: A Nash Equilibrium Perspective","created":"2026-02-06","cited_by_count":0,"area":"alignment"},{"id":"2603.14664","title":"Punctuated Equilibria in Artificial Intelligence: The Institutional Scaling Law and the Speciation of Sovereign AI","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2605.18799","title":"ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning","created":"2026-05-11","cited_by_count":0,"area":"lr"}],"next_cursor":null}