{"total":108,"rows":[{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330,"area":"lr"},{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053,"area":"lr"},{"id":"2412.19437","title":"DeepSeek-V3 Technical Report","created":"2024-12-27","cited_by_count":811,"area":"lr"},{"id":"2406.04692","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","created":"2024-06-07","cited_by_count":438,"area":"lr"},{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346,"area":"lr"},{"id":"2501.03262","title":"REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization","created":"2025-01-04","cited_by_count":241,"area":"lr"},{"id":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223,"area":"lr"},{"id":"2505.19590","title":"Learning to Reason without External Rewards","created":"2025-05-26","cited_by_count":210,"area":"lr"},{"id":"2406.09961","title":"ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation","created":"2024-06-14","cited_by_count":129,"area":"lr"},{"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":"2406.09279","title":"Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback","created":"2024-06-13","cited_by_count":107,"area":"lr"},{"id":"2510.14901","title":"Reasoning with Sampling: Your Base Model is Smarter Than You Think","created":"2025-10-16","cited_by_count":89,"area":"lr"},{"id":"2504.00050","title":"JudgeLRM: Large Reasoning Models as a Judge","created":"2025-03-31","cited_by_count":78,"area":"lr"},{"id":"2501.12368","title":"InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model","created":"2025-01-21","cited_by_count":74,"area":"lr"},{"id":"2505.14631","title":"Think Only When You Need with Large Hybrid-Reasoning Models","created":"2025-05-20","cited_by_count":66,"area":"lr"},{"id":"2602.05125","title":"Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks","created":"2026-02-04","cited_by_count":62,"area":"lr"},{"id":"2502.00674","title":"Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?","created":"2025-02-02","cited_by_count":54,"area":"lr"},{"id":"2501.18101","title":"Diverse Preference Optimization","created":"2025-01-30","cited_by_count":52,"area":"lr"},{"id":"2504.15253","title":"Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators","created":"2025-04-21","cited_by_count":44,"area":"lr"},{"id":"2506.09942","title":"VerIF: Verification Engineering for Reinforcement Learning in Instruction Following","created":"2025-06-11","cited_by_count":44,"area":"lr"},{"id":"2502.11689","title":"Improve LLM-as-a-Judge Ability as a General Ability","created":"2025-02-17","cited_by_count":37,"area":"lr"},{"id":"2505.02018","title":"R-Bench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning Evaluation","created":"2025-05-04","cited_by_count":34,"area":"lr"},{"id":"2507.23751","title":"CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks","created":"2025-07-31","cited_by_count":32,"area":"lr"},{"id":"2412.17596","title":"Evaluating LLMs' Divergent Thinking Capabilities for Scientific Idea Generation with Minimal Context","created":"2024-12-23","cited_by_count":28,"area":"lr"},{"id":"2511.16660","title":"Cognitive Foundations for Reasoning and Their Manifestation in LLMs","created":"2025-11-20","cited_by_count":26,"area":"lr"},{"id":"2408.13518","title":"Selective Preference Optimization via Token-Level Reward Function Estimation","created":"2024-08-24","cited_by_count":25,"area":"lr"},{"id":"2409.12452","title":"Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning","created":"2024-09-19","cited_by_count":25,"area":"lr"},{"id":"2504.01995","title":"Brains vs. Bytes: Evaluating LLM Proficiency in Olympiad Mathematics","created":"2025-04-01","cited_by_count":24,"area":"lr"},{"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":"2505.14625","title":"TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning","created":"2025-05-20","cited_by_count":21,"area":"lr"},{"id":"2502.12501","title":"Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge","created":"2025-02-18","cited_by_count":19,"area":"lr"},{"id":"2503.07478","title":"VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models","created":"2025-03-10","cited_by_count":19,"area":"lr"},{"id":"2507.09662","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","created":"2025-07-13","cited_by_count":18,"area":"lr"},{"id":"2503.04378","title":"HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks","created":"2025-03-06","cited_by_count":17,"area":"lr"},{"id":"2503.04381","title":"TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-Judge","created":"2025-03-06","cited_by_count":17,"area":"lr"},{"id":"2502.05605","title":"Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization","created":"2025-02-08","cited_by_count":16,"area":"lr"},{"id":"2508.17784","title":"Proximal Supervised Fine-Tuning","created":"2025-08-25","cited_by_count":16,"area":"lr"},{"id":"2501.16154","title":"AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought","created":"2025-01-27","cited_by_count":14,"area":"lr"},{"id":"2604.06628","title":"Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability","created":"2026-04-08","cited_by_count":14,"area":"lr"},{"id":"2410.04698","title":"MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs","created":"2024-10-07","cited_by_count":13,"area":"lr"},{"id":"2502.08922","title":"Self-Consistency of the Internal Reward Models Improves Self-Rewarding Language Models","created":"2025-02-13","cited_by_count":13,"area":"lr"},{"id":"2503.19877","title":"Scaling Evaluation-time Compute with Reasoning Models as Evaluators","created":"2025-03-25","cited_by_count":13,"area":"lr"},{"id":"2506.08390","title":"On Reasoning Strength Planning in Large Reasoning Models","created":"2025-06-10","cited_by_count":13,"area":"lr"},{"id":"2506.20100","title":"MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations","created":"2025-06-25","cited_by_count":13,"area":"lr"},{"id":"2512.05111","title":"ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning","created":"2025-12-04","cited_by_count":13,"area":"lr"},{"id":"2501.11877","title":"From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning","created":"2025-01-21","cited_by_count":12,"area":"lr"},{"id":"2602.17025","title":"WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning","created":"2026-02-19","cited_by_count":12,"area":"lr"},{"id":"2505.12601","title":"Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers","created":"2025-05-19","cited_by_count":11,"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":"2410.07035","title":"PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness","created":"2024-10-09","cited_by_count":9,"area":"lr"},{"id":"2602.02301","title":"Advancing General-Purpose Reasoning Models with Modular Gradient Surgery","created":"2026-02-02","cited_by_count":9,"area":"lr"},{"id":"2411.07240","title":"UTMath: Math Evaluation with Unit Test via Reasoning-to-Coding Thoughts","created":"2024-11-11","cited_by_count":8,"area":"lr"},{"id":"2511.11113","title":"VIDEOP2R: Video Understanding from Perception to Reasoning","created":"2025-11-14","cited_by_count":8,"area":"lr"},{"id":"2601.13433","title":"Who Endorsed It? Measuring Authority Bias Across Expertise Levels in Language Models","created":"2026-01-19","cited_by_count":8,"area":"lr"},{"id":"2601.22588","title":"Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry","created":"2026-01-30","cited_by_count":8,"area":"lr"},{"id":"2604.22709","title":"Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought","created":"2026-04-24","cited_by_count":8,"area":"lr"},{"id":"2505.23816","title":"A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMs","created":"2025-05-27","cited_by_count":7,"area":"lr"},{"id":"2512.19126","title":"AWPO: Enhancing Tool-Use of Large Language Models through Adaptive Integration of Reasoning Rewards","created":"2025-12-22","cited_by_count":7,"area":"lr"},{"id":"2601.21051","title":"Llama-3.1-FoundationAI-SecurityLLM-Reasoning-8B Technical Report","created":"2026-01-28","cited_by_count":7,"area":"lr"},{"id":"2605.26958","title":"Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation","created":"2026-05-26","cited_by_count":7,"area":"lr"},{"id":"2502.14643","title":"Length-Controlled Margin-Based Preference Optimization without Reference Model","created":"2025-02-20","cited_by_count":6,"area":"lr"},{"id":"2502.16944","title":"Pretrain Value, Not Reward: Decoupled Value Policy Optimization","created":"2025-02-24","cited_by_count":6,"area":"lr"},{"id":"2507.08068","title":"Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions","created":"2025-07-10","cited_by_count":6,"area":"lr"},{"id":"2602.12135","title":"WavBench: Benchmarking Reasoning, Colloquialism, and Paralinguistics for End-to-End Spoken Dialogue Models","created":"2026-02-12","cited_by_count":6,"area":"lr"},{"id":"2509.04334","title":"GeoArena: Evaluating Open-World Geographic Reasoning in Large Vision-Language Models","created":"2025-09-04","cited_by_count":5,"area":"lr"},{"id":"2511.07922","title":"SERL: Self-Examining Reinforcement Learning on Open-Domain","created":"2025-11-11","cited_by_count":5,"area":"lr"},{"id":"2603.04597","title":"Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning","created":"2026-03-04","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2410.12997","title":"\"Let's Argue Both Sides\": Argument Generation Can Force Small Models to Utilize Previously Inaccessible Reasoning Capabilities","created":"2024-10-16","cited_by_count":4,"area":"lr"},{"id":"2507.21645","title":"Libra: Assessing and Improving Reward Model by Learning to Think","created":"2025-07-29","cited_by_count":4,"area":"lr"},{"id":"2508.20151","title":"IntentionReasoner: Facilitating Adaptive LLM Safeguards through Intent Reasoning and Selective Query Refinement","created":"2025-08-27","cited_by_count":4,"area":"lr"},{"id":"2509.14760","title":"Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation","created":"2025-09-18","cited_by_count":4,"area":"lr"},{"id":"2412.18011","title":"StructTest: Benchmarking LLMs' Reasoning through Compositional Structured Outputs","created":"2024-12-23","cited_by_count":3,"area":"lr"},{"id":"2506.12704","title":"Flexible Realignment of Language Models","created":"2025-06-15","cited_by_count":3,"area":"lr"},{"id":"2603.21016","title":"Mitigating Selection Bias in Large Language Models via Permutation-Aware GRPO","created":"2026-03-22","cited_by_count":3,"area":"lr"},{"id":"2406.12269","title":"Unveiling Implicit Table Knowledge with Question-Then-Pinpoint Reasoner for Insightful Table Summarization","created":"2024-06-18","cited_by_count":2,"area":"lr"},{"id":"2502.19622","title":"Weaker LLMs' Opinions Also Matter: Mixture of Opinions Enhances LLM's Mathematical Reasoning","created":"2025-02-26","cited_by_count":2,"area":"lr"},{"id":"2508.18736","title":"Rethinking Caching for LLM Serving Systems: Beyond Traditional Heuristics","created":"2025-08-26","cited_by_count":2,"area":"lr"},{"id":"2601.03969","title":"Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models","created":"2026-01-07","cited_by_count":2,"area":"lr"},{"id":"2601.18730","title":"Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale","created":"2026-01-26","cited_by_count":2,"area":"lr"},{"id":"2606.29689","title":"Can MLLMs Critique Like Humans? Evaluating Open-Ended Aesthetic Reasoning in Multimodal Large Language Models","created":"2026-06-29","cited_by_count":2,"area":"lr"},{"id":"2510.14200","title":"RLSR: Reinforcement Learning with Supervised Reward Outperforms SFT in Instruction Following","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2510.23868","title":"GIFT: Group-Relative Implicit Fine-Tuning Integrates GRPO with DPO and UNA","created":"2025-10-27","cited_by_count":1,"area":"lr"},{"id":"2601.18760","title":"Beyond Preferences: Learning Alignment Principles Grounded in Human Reasons and Values","created":"2026-01-26","cited_by_count":1,"area":"lr"},{"id":"2602.11530","title":"PASCAL: A Phase-Aware Scheduling Algorithm for Serving Reasoning-based Large Language Models","created":"2026-02-12","cited_by_count":1,"area":"lr"},{"id":"2603.08704","title":"Evaluating Financial Intelligence in Large Language Models: Benchmarking SuperInvesting AI with LLM Engines","created":"2026-03-09","cited_by_count":1,"area":"lr"},{"id":"2604.06505","title":"MedConclusion: A Benchmark for Biomedical Conclusion Generation from Structured Abstracts","created":"2026-04-07","cited_by_count":1,"area":"lr"},{"id":"2605.10158","title":"Unsupervised Process Reward Models","created":"2026-05-11","cited_by_count":1,"area":"lr"},{"id":"2605.29656","title":"TRACE: Toulmin-based Reasoning Assessment through Constructive Elements for LLM CoT Evaluation","created":"2026-05-28","cited_by_count":1,"area":"lr"},{"id":"2606.10307","title":"Early-Token Confidence Predicts Reasoning Quality in Multi-Agent LLM Debate","created":"2026-06-09","cited_by_count":1,"area":"lr"},{"id":"2608.09271","title":"SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation","created":"2026-08-10","cited_by_count":1,"area":"lr"},{"id":"2412.09385","title":"AI Predicts AGI: Leveraging AGI Forecasting and Peer Review to Explore LLMs' Complex Reasoning Capabilities","created":"2024-12-12","cited_by_count":0,"area":"lr"},{"id":"2509.24207","title":"Humanline: Online Alignment as Perceptual Loss","created":"2025-09-29","cited_by_count":0,"area":"lr"},{"id":"2510.17388","title":"The Atomic Instruction Gap: Instruction-Tuned LLMs Struggle with Simple, Self-Contained Directives","created":"2025-10-20","cited_by_count":0,"area":"lr"},{"id":"2604.08999","title":"ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answering","created":"2026-04-10","cited_by_count":0,"area":"lr"},{"id":"2605.29009","title":"Label-Free Reinforcement Learning via Cross-Model Entropy","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.04806","title":"NoRA: Evaluating Grounded Reasonableness in Visual First-person Normative Action Reasoning","created":"2026-06-03","cited_by_count":0,"area":"lr"},{"id":"2607.08758","title":"Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation","created":"2026-07-09","cited_by_count":0,"area":"lr"},{"id":"2607.18438","title":"Relay-Bench: Evaluating LLMs on Multi-Domain Reasoning Chains","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2608.08889","title":"LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing","created":"2026-08-09","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}