{"total":108,"rows":[{"id":"2601.05242","title":"GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization","created":"2026-01-08","cited_by_count":193,"area":"lr"},{"id":"2502.17424","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","created":"2025-02-24","cited_by_count":172,"area":"safety"},{"id":"2511.00088","title":"Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail","created":"2025-10-30","cited_by_count":146,"area":"lr"},{"id":"2510.07743","title":"OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment","created":"2025-10-09","cited_by_count":132,"area":"alignment"},{"id":"2508.12790","title":"Reinforcement Learning with Rubric Anchors","created":"2025-08-18","cited_by_count":113,"area":"lr"},{"id":"2502.12659","title":"The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1","created":"2025-02-18","cited_by_count":91,"area":"lr"},{"id":"2412.10400","title":"Reinforcement Learning Enhanced LLMs: A Survey","created":"2024-12-05","cited_by_count":71,"area":"lr"},{"id":"2507.08794","title":"One Token to Fool LLM-as-a-Judge","created":"2025-07-11","cited_by_count":60,"area":"alignment"},{"id":"2509.01322","title":"LongCat-Flash Technical Report","created":"2025-09-01","cited_by_count":58,"area":"agents"},{"id":"2508.09224","title":"From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training","created":"2025-08-12","cited_by_count":52,"area":null},{"id":"2502.19328","title":"Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems","created":"2025-02-26","cited_by_count":51,"area":"lr"},{"id":"2411.18203","title":"Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning","created":"2024-11-27","cited_by_count":50,"area":"lr"},{"id":"2505.11711","title":"Reinforcement Learning Finetunes Small Subnetworks in Large Language Models","created":"2025-05-16","cited_by_count":49,"area":null},{"id":"2502.12970","title":"Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking","created":"2025-02-18","cited_by_count":34,"area":"lr"},{"id":"2506.04185","title":"R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning","created":"2025-06-04","cited_by_count":34,"area":"lr"},{"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":"2509.17158","title":"ARE: Scaling Up Agent Environments and Evaluations","created":"2025-09-21","cited_by_count":30,"area":"agents"},{"id":"2510.17314","title":"Auto-Rubric: Learning From Implicit Weights to Explicit Rubrics for Reward Modeling","created":"2025-10-20","cited_by_count":30,"area":"alignment"},{"id":"2502.01042","title":"SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals","created":"2025-02-03","cited_by_count":29,"area":"safety"},{"id":"2502.20127","title":"SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning","created":"2025-02-27","cited_by_count":28,"area":"lr"},{"id":"2503.16431","title":"OpenAI's Approach to External Red Teaming for AI Models and Systems","created":"2025-01-24","cited_by_count":28,"area":"safety"},{"id":"2506.08123","title":"QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA","created":"2025-06-09","cited_by_count":28,"area":"alignment"},{"id":"2504.09420","title":"SaRO: Enhancing LLM Safety through Reasoning-based Alignment","created":"2025-04-13","cited_by_count":26,"area":"lr"},{"id":"2412.18693","title":"Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning","created":"2024-12-24","cited_by_count":25,"area":"safety"},{"id":"2503.04474","title":"Know Thy Judge: On the Robustness Meta-Evaluation of LLM Safety Judges","created":"2025-03-06","cited_by_count":24,"area":"safety"},{"id":"2510.16380","title":"MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes","created":"2025-10-18","cited_by_count":23,"area":"lr"},{"id":"2502.11555","title":"Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models","created":"2025-02-17","cited_by_count":22,"area":"alignment"},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20,"area":"agents"},{"id":"2507.17842","title":"Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning","created":"2025-07-23","cited_by_count":19,"area":"lr"},{"id":"2411.11504","title":"Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering","created":"2024-11-18","cited_by_count":16,"area":null},{"id":"2505.16265","title":"Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models","created":"2025-05-22","cited_by_count":16,"area":"lr"},{"id":"2505.23559","title":"SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents","created":"2025-05-29","cited_by_count":16,"area":"agents"},{"id":"2508.12733","title":"LinguaSafe: A Comprehensive Multilingual Safety Benchmark for Large Language Models","created":"2025-08-18","cited_by_count":16,"area":"safety"},{"id":"2502.04040","title":"Safety Reasoning with Guidelines","created":"2025-02-06","cited_by_count":15,"area":"lr"},{"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":"2507.14987","title":"AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning","created":"2025-07-20","cited_by_count":15,"area":"alignment"},{"id":"2504.07165","title":"Perception in Reflection","created":"2025-04-09","cited_by_count":13,"area":"mllm"},{"id":"2510.07686","title":"Stress-Testing Model Specs Reveals Character Differences among Language Models","created":"2025-10-09","cited_by_count":13,"area":null},{"id":"2504.04524","title":"Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning","created":"2025-04-06","cited_by_count":12,"area":"lr"},{"id":"2509.19249","title":"Reinforcement Learning on Pre-Training Data","created":"2025-09-23","cited_by_count":12,"area":"lr"},{"id":"2412.16974","title":"Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs","created":"2024-12-22","cited_by_count":11,"area":"alignment"},{"id":"2601.18984","title":"Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning","created":"2026-01-26","cited_by_count":11,"area":"lr"},{"id":"2603.20882","title":"RubricRAG: Towards Interpretable and Reliable LLM Evaluation via Domain Knowledge Retrieval for Rubric Generation","created":"2026-03-21","cited_by_count":11,"area":null},{"id":"2510.08240","title":"The Alignment Waltz: Jointly Training Agents to Collaborate for Safety","created":"2025-10-09","cited_by_count":10,"area":"agents"},{"id":"2510.17017","title":"SafeSearch: Do Not Trade Safety for Utility in LLM Search Agents","created":"2025-10-19","cited_by_count":9,"area":"agents"},{"id":"2502.00718","title":"\"I am bad\": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models","created":"2025-02-02","cited_by_count":8,"area":"safety"},{"id":"2505.20309","title":"Guiding Giants: Lightweight Controllers for Weighted Activation Steering in LLMs","created":"2025-05-22","cited_by_count":8,"area":"mechinterp"},{"id":"2506.06414","title":"Benchmarking Misuse Mitigation Against Covert Adversaries","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2509.21319","title":"RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards","created":"2025-09-25","cited_by_count":8,"area":"alignment"},{"id":"2510.16582","title":"Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?","created":"2025-10-18","cited_by_count":8,"area":"rag"},{"id":"2605.27823","title":"Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security","created":"2026-05-27","cited_by_count":8,"area":"safety"},{"id":"2501.18626","title":"The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs","created":"2025-01-27","cited_by_count":7,"area":"safety"},{"id":"2505.21908","title":"Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding","created":"2025-05-28","cited_by_count":7,"area":"lr"},{"id":"2603.11388","title":"Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment","created":"2026-03-12","cited_by_count":7,"area":"alignment"},{"id":"2501.15453","title":"Data-adaptive Safety Rules for Training Reward Models","created":"2025-01-26","cited_by_count":6,"area":"alignment"},{"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":"2507.01368","title":"Activation Reward Models for Few-Shot Model Alignment","created":"2025-07-02","cited_by_count":6,"area":"mllm"},{"id":"2510.23272","title":"Code Aesthetics with Agentic Reward Feedback","created":"2025-10-27","cited_by_count":6,"area":"agents"},{"id":"2603.15646","title":"Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy","created":"2026-03-04","cited_by_count":6,"area":"alignment"},{"id":"2504.02193","title":"More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment","created":"2025-04-03","cited_by_count":5,"area":"alignment"},{"id":"2510.11407","title":"KnowRL: Teaching Language Models to Know What They Know","created":"2025-10-13","cited_by_count":5,"area":null},{"id":"2503.20995","title":"ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models","created":"2025-03-26","cited_by_count":4,"area":"alignment"},{"id":"2506.08266","title":"Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints","created":"2025-06-09","cited_by_count":4,"area":"alignment"},{"id":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2603.12011","title":"Can RL Improve Generalization of LLM Agents? An Empirical Study","created":"2026-03-12","cited_by_count":4,"area":"agents"},{"id":"2607.09375","title":"Mach-Mind-4-Flash Technical Report","created":"2026-07-10","cited_by_count":4,"area":"agents"},{"id":"2506.02460","title":"MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework","created":"2025-06-03","cited_by_count":3,"area":"alignment"},{"id":"2512.20061","title":"Scaling Reinforcement Learning for Content Moderation with Large Language Models","created":"2025-12-23","cited_by_count":3,"area":null},{"id":"2604.13618","title":"C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences","created":"2026-04-15","cited_by_count":3,"area":"alignment"},{"id":"2605.05750","title":"RVPO: Risk-Sensitive Alignment via Variance Regularization","created":"2026-05-07","cited_by_count":3,"area":"alignment"},{"id":"2605.31328","title":"Reinforcement Learning Can Amplify Emergent Misalignment from Harmless Rewards","created":"2026-05-29","cited_by_count":3,"area":"alignment"},{"id":"2606.07705","title":"SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models","created":"2026-06-05","cited_by_count":3,"area":"alignment"},{"id":"2608.02831","title":"Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning","created":"2026-08-03","cited_by_count":3,"area":null},{"id":"2608.27505","title":"A Survey on Rubric-Guided Reinforcement Learning for Language Models","created":"2026-08-27","cited_by_count":3,"area":"alignment"},{"id":"2506.10389","title":"EQA-RM: A Generative Embodied Reward Model with Test-time Scaling","created":"2025-06-12","cited_by_count":2,"area":"lr"},{"id":"2507.17107","title":"Reinforcement Learning Fine-Tunes a Sparse Subnetwork in Large Language Models","created":"2025-07-23","cited_by_count":2,"area":"alignment"},{"id":"2511.09864","title":"Uncertainty-Guided Checkpoint Selection for Reinforcement Finetuning of Large Language Models","created":"2025-11-13","cited_by_count":2,"area":"alignment"},{"id":"2601.03725","title":"EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuning","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2602.13562","title":"Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning","created":"2026-02-14","cited_by_count":2,"area":"lr"},{"id":"2603.10938","title":"Safe RLHF Beyond Expectation: Stochastic Dominance for Universal Spectral Risk Control","created":"2026-03-11","cited_by_count":2,"area":"alignment"},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2606.28182","title":"LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior","created":"2026-06-26","cited_by_count":2,"area":"agents"},{"id":"2411.10534","title":"Chain of Alignment: Integrating Public Will with Expert Intelligence for Language Model Alignment","created":"2024-11-15","cited_by_count":1,"area":"alignment"},{"id":"2506.06444","title":"Saffron-1: Safety Inference Scaling","created":"2025-06-06","cited_by_count":1,"area":"alignment"},{"id":"2509.15932","title":"The Alignment Bottleneck","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2602.02595","title":"To Defend Against Cyber Attacks, We Must Teach AI Agents to Hack","created":"2026-02-01","cited_by_count":1,"area":"safety"},{"id":"2602.03195","title":"Reinforcement Learning with Promising Tokens for Large Language Models","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2602.05110","title":"Understanding LLM Evaluator Behavior: A Structured Multi-Evaluator Framework for Merchant Risk Assessment","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2606.03968","title":"QUBRIC: Co-Designing Queries and Rubrics for RL Beyond Verifiable Rewards","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.19168","title":"Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection","created":"2026-06-17","cited_by_count":1,"area":"alignment"},{"id":"2608.12654","title":"SteerBench-Work: A Benchmark for Agent Steering at Action Boundaries","created":"2026-08-12","cited_by_count":1,"area":"agents"},{"id":"2503.04784","title":"KunlunBaize: LLM with Multi-Scale Convolution and Multi-Token Prediction Under TransformerX Framework","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2505.18040","title":"Contrastive Distillation of Emotion Knowledge from LLMs for Zero-Shot Emotion Recognition","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2506.10020","title":"From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment","created":"2025-06-07","cited_by_count":0,"area":"alignment"},{"id":"2602.02258","title":"Alignment-Aware Model Adaptation via Feedback-Guided Optimization","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2604.01354","title":"Open-Domain Safety Policy Construction","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.04144","title":"Many Preferences, Few Policies: Towards Scalable Language Model Personalization","created":"2026-04-05","cited_by_count":0,"area":"alignment"},{"id":"2604.13398","title":"From Prediction to Justification: Aligning Sentiment Reasoning with Human Rationale via Reinforcement Learning","created":"2026-04-15","cited_by_count":0,"area":"lr"},{"id":"2605.20994","title":"Towards Context-Invariant Safety Alignment for Large Language Models","created":"2026-05-20","cited_by_count":0,"area":"alignment"},{"id":"2607.24484","title":"What do Reward Models Memorize?","created":"2026-07-27","cited_by_count":0,"area":"alignment"}],"next_cursor":"100"}