{"total":88,"rows":[{"id":"2504.11468","title":"SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models","created":"2025-04-10","cited_by_count":212,"area":"lr"},{"id":"2508.19652","title":"Self-Rewarding Vision-Language Model via Reasoning Decomposition","created":"2025-08-27","cited_by_count":97,"area":"lr"},{"id":"2506.10943","title":"Self-Adapting Language Models","created":"2025-06-12","cited_by_count":84,"area":null},{"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":"2506.19248","title":"Inference-Time Reward Hacking in Large Language Models","created":"2025-06-24","cited_by_count":34,"area":"alignment"},{"id":"2509.24372","title":"Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning","created":"2025-09-29","cited_by_count":34,"area":null},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2506.03637","title":"RewardAnything: Generalizable Principle-Following Reward Models","created":"2025-06-04","cited_by_count":28,"area":"alignment"},{"id":"2605.12474","title":"Reward Hacking in Rubric-Based Reinforcement Learning","created":"2026-05-12","cited_by_count":26,"area":"alignment"},{"id":"2512.16301","title":"Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills","created":"2025-12-18","cited_by_count":22,"area":"agents"},{"id":"2507.04136","title":"A Technical Survey of Reinforcement Learning Techniques for Large Language Models","created":"2025-07-05","cited_by_count":21,"area":"lr"},{"id":"2509.10147","title":"Virtual Agent Economies","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2511.12344","title":"Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning","created":"2025-11-15","cited_by_count":21,"area":"lr"},{"id":"2510.06445","title":"A Survey on Agentic Security: Applications, Threats and Defenses","created":"2025-10-07","cited_by_count":20,"area":"agents"},{"id":"2508.19598","title":"Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning","created":"2025-08-27","cited_by_count":17,"area":"agents"},{"id":"2606.04923","title":"Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning","created":"2026-06-03","cited_by_count":16,"area":"alignment"},{"id":"2509.25026","title":"GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing Reasoning","created":"2025-09-29","cited_by_count":15,"area":"lr"},{"id":"2506.15651","title":"AutoRule: Reasoning Chain-of-thought Extracted Rule-based Rewards Improve Preference Learning","created":"2025-06-18","cited_by_count":14,"area":"lr"},{"id":"2511.09586","title":"Environment Scaling for Interactive Agentic Experience Collection: A Survey","created":"2025-11-12","cited_by_count":13,"area":"agents"},{"id":"2506.01183","title":"Doubly Robust Alignment for Large Language Models","created":"2025-06-01","cited_by_count":12,"area":"alignment"},{"id":"2507.07375","title":"Bradley-Terry and Multi-Objective Reward Modeling Are Complementary","created":"2025-07-10","cited_by_count":11,"area":"alignment"},{"id":"2509.19333","title":"Pluralistic Off-policy Evaluation and Alignment","created":"2025-09-15","cited_by_count":11,"area":"alignment"},{"id":"2605.29847","title":"EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation","created":"2026-05-28","cited_by_count":11,"area":"synth"},{"id":"2504.05294","title":"Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations","created":"2025-04-07","cited_by_count":9,"area":"lr"},{"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":"2602.19526","title":"How to Train Your Deep Research Agent? Prompt, Reward, and Policy Optimization in Search-R1","created":"2026-02-23","cited_by_count":8,"area":"agents"},{"id":"2506.00042","title":"Enhancing Tool Learning in Large Language Models with Hierarchical Error Checklists","created":"2025-05-28","cited_by_count":7,"area":"agents"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2603.10535","title":"Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning","created":"2026-03-11","cited_by_count":7,"area":"alignment"},{"id":"2605.14220","title":"Diagnosing Training Inference Mismatch in LLM Reinforcement Learning via a Zero-Mismatch Reference","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2505.10597","title":"Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment","created":"2025-05-15","cited_by_count":6,"area":"alignment"},{"id":"2606.19818","title":"Uncertainty-Aware Reward Modeling for Stable RLHF","created":"2026-06-18","cited_by_count":6,"area":"alignment"},{"id":"2504.20157","title":"Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models","created":"2025-04-28","cited_by_count":5,"area":"lr"},{"id":"2508.02618","title":"Alleviating Attention Hacking in Discriminative Reward Modeling through Interaction Distillation","created":"2025-08-04","cited_by_count":5,"area":"alignment"},{"id":"2510.14176","title":"ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning","created":"2025-10-16","cited_by_count":5,"area":"deeprl"},{"id":"2604.16242","title":"Detecting and Suppressing Reward Hacking with Gradient Fingerprints","created":"2026-04-17","cited_by_count":5,"area":"alignment"},{"id":"2607.21273","title":"The Dark Room in the Reward Channel: Dense Prediction Rewards Collapse GRPO-Trained LLM Agents -- and The Channel, Not the Content, Decides What Works","created":"2026-07-23","cited_by_count":5,"area":"lr"},{"id":"2510.25368","title":"Position: Biology is the Challenge Physics-Informed ML Needs to Evolve","created":"2025-10-29","cited_by_count":4,"area":null},{"id":"2605.04266","title":"Explaining and Preventing Alignment Collapse in Iterative RLHF","created":"2026-05-05","cited_by_count":4,"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":"2602.05380","title":"SAIL: Self-Amplified Iterative Learning for Diffusion Model Alignment with Minimal Human Feedback","created":"2026-02-05","cited_by_count":3,"area":"diffusion"},{"id":"2603.03291","title":"One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models","created":"2026-02-06","cited_by_count":3,"area":"alignment"},{"id":"2605.04431","title":"Towards Robust LLM Post-Training: Automatic Failure Management for Reinforcement Fine-Tuning","created":"2026-05-06","cited_by_count":3,"area":null},{"id":"2605.06036","title":"Optimal Transport for LLM Reward Modeling from Noisy Preference","created":"2026-05-07","cited_by_count":3,"area":"alignment"},{"id":"2605.20061","title":"Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents","created":"2026-05-19","cited_by_count":3,"area":"agents"},{"id":"2608.09682","title":"Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning","created":"2026-08-10","cited_by_count":3,"area":"lr"},{"id":"2504.16272","title":"Learning Explainable Dense Reward Shapes via Bayesian Optimization","created":"2025-04-22","cited_by_count":2,"area":"alignment"},{"id":"2601.15690","title":"From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2602.02572","title":"Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective","created":"2026-01-31","cited_by_count":2,"area":"alignment"},{"id":"2602.09653","title":"ClinAlign: Scaling Healthcare Alignment from Clinician Preference","created":"2026-02-10","cited_by_count":2,"area":"alignment"},{"id":"2603.02239","title":"Engineering Reasoning and Instruction (ERI) Benchmark: A Large Taxonomy-driven Dataset for Foundation Models and Agents","created":"2026-02-16","cited_by_count":2,"area":"lr"},{"id":"2604.15705","title":"Towards Robust Endogenous Reasoning: Unifying Drift Adaptation in Non-Stationary Tuning","created":"2026-04-17","cited_by_count":2,"area":"lr"},{"id":"2607.09492","title":"Multimodal Reward Hacking in Reinforcement Learning","created":"2026-07-10","cited_by_count":2,"area":"mllm"},{"id":"2609.00213","title":"Uncovering and Mitigating Aggregation-Induced Reward Hacking in Multi-Reward Reinforcement Learning","created":"2026-08-31","cited_by_count":2,"area":"alignment"},{"id":"2503.22480","title":"Probabilistic Uncertain Reward Model","created":"2025-03-28","cited_by_count":1,"area":"alignment"},{"id":"2509.14659","title":"Aligning Audio Captions with Human Preferences","created":"2025-09-18","cited_by_count":1,"area":"alignment"},{"id":"2510.13036","title":"Repairing Reward Functions with Feedback to Mitigate Reward Hacking","created":"2025-10-14","cited_by_count":1,"area":"alignment"},{"id":"2601.21350","title":"Factored Causal Representation Learning for Robust Reward Modeling in RLHF","created":"2026-01-29","cited_by_count":1,"area":"alignment"},{"id":"2602.06195","title":"DeDPO: Debiased Direct Preference Optimization for Diffusion Models","created":"2026-02-05","cited_by_count":1,"area":"diffusion"},{"id":"2604.19752","title":"Soft-Label Governance for Distributional Safety in Multi-Agent Systems","created":"2026-03-19","cited_by_count":1,"area":"agents"},{"id":"2605.08496","title":"Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms","created":"2026-05-08","cited_by_count":1,"area":"safety"},{"id":"2605.18721","title":"General Preference Reinforcement Learning","created":"2026-05-18","cited_by_count":1,"area":"alignment"},{"id":"2605.19723","title":"Mathematical Reasoning in Large Language Models: Benchmarks, Architectures, Evaluation, and Open Challenges","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2606.28294","title":"Democratic ICAI: Debating Our Way to Steering Principles from Preferences","created":"2026-06-26","cited_by_count":1,"area":"alignment"},{"id":"2607.16492","title":"WeedExpert-R1: Incentivizing Botanical Reasoning in MLLMs with Reinforcement Learning for Precision Weed Grounding","created":"2026-07-17","cited_by_count":1,"area":"lr"},{"id":"2609.03955","title":"Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2609.19164","title":"Advantage Scale Calibration Imbalance in Group-Relative Optimization under Low-Variance Rewards: Diagnosis and Bounded Recovery","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2508.09155","title":"A Rolling Stone Gathers No Moss: Adaptive Policy Optimization for Stable Self-Evaluation in Large Multimodal Models","created":"2025-08-05","cited_by_count":0,"area":"alignment"},{"id":"2509.10509","title":"The Anti-Ouroboros Effect: Emergent Resilience in Large Language Models from Recursive Selective Feedback","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2509.24713","title":"Circuit-Aware Reward Training: A Mechanistic Framework for Longtail Robustness in RLHF","created":"2025-09-29","cited_by_count":0,"area":"alignment"},{"id":"2510.05283","title":"Beyond Monolithic Rewards: A Hybrid and Multi-Aspect Reward Optimization for MLLM Alignment","created":"2025-10-06","cited_by_count":0,"area":"mllm"},{"id":"2510.18619","title":"Visual Attention Reasoning via Hierarchical Search and Self-Verification","created":"2025-10-21","cited_by_count":0,"area":"lr"},{"id":"2511.23092","title":"Does Self-Evaluation Enable Wireheading in Language Models?","created":"2025-11-28","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":"2602.03305","title":"medR: Reward Engineering for Clinical Offline Reinforcement Learning via Tri-Drive Potential Functions","created":"2026-02-03","cited_by_count":0,"area":"offlinerl"},{"id":"2603.01641","title":"Learning Structured Reasoning via Tractable Trajectory Control","created":"2026-03-02","cited_by_count":0,"area":"lr"},{"id":"2604.17328","title":"Rethinking the Comparison Unit in Sequence-Level Reinforcement Learning: An Equal-Length Paired Training Framework from Loss Correction to Sample Construction","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2605.11865","title":"Variance-aware Reward Modeling with Anchor Guidance","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2605.13411","title":"Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution","created":"2026-05-13","cited_by_count":0,"area":"safety"},{"id":"2606.10528","title":"Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output","created":"2026-06-09","cited_by_count":0,"area":"alignment"},{"id":"2606.16236","title":"Evolutionary Bilevel Reward Shaping for Generalization in Reinforcement Learning","created":"2026-06-15","cited_by_count":0,"area":"deeprl"},{"id":"2606.25757","title":"OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning","created":"2026-06-24","cited_by_count":0,"area":"lr"},{"id":"2606.26917","title":"GEOALIGN: Geometric Rollout Curation for Robust LLM Reinforcement Learning","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2608.29280","title":"RAGDiffusion++: From Macro-Retrieval to Micro-Fidelity Alignment for Garment Generation","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.00064","title":"Attention Sensitivity Is Not Enough: Dissociating Attention-Level and Behavioural In-Context Learning under Fine-Tuning","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.20156","title":"QUALS: Corpus Equilibrium for Universal Forecasting via Pattern Quantization and Learnability Synchronization","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.23457","title":"RLVR$^{2}$: Reinforcement Learning with Verifiable Rubric-based Ranking","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2610.10273","title":"A Closed-Loop Non-Asymptotic Convergence Analysis of PPO with Learned Critics and Clipping","created":"2026-10-07","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}