{"total":102,"rows":[{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2410.07163","title":"Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning","created":"2024-10-09","cited_by_count":172,"area":"lr"},{"id":"2504.09037","title":"A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems","created":"2025-04-12","cited_by_count":111,"area":"lr"},{"id":"2411.04991","title":"Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives","created":"2024-11-07","cited_by_count":48,"area":"lr"},{"id":"2504.04736","title":"Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use","created":"2025-04-07","cited_by_count":45,"area":"lr"},{"id":"2410.05318","title":"Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification","created":"2024-10-05","cited_by_count":40,"area":"lr"},{"id":"2406.17169","title":"Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models","created":"2024-06-24","cited_by_count":39,"area":"lr"},{"id":"2503.12854","title":"Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation","created":"2025-03-17","cited_by_count":37,"area":"lr"},{"id":"2407.00782","title":"Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning","created":"2024-06-30","cited_by_count":35,"area":"lr"},{"id":"2404.10346","title":"Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards","created":"2024-04-16","cited_by_count":31,"area":"lr"},{"id":"2505.17508","title":"On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning","created":"2025-05-23","cited_by_count":30,"area":"lr"},{"id":"2502.04404","title":"Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models","created":"2025-02-06","cited_by_count":27,"area":"lr"},{"id":"2506.08379","title":"Reinforce LLM Reasoning through Multi-Agent Reflection","created":"2025-06-10","cited_by_count":27,"area":"lr"},{"id":"2504.09420","title":"SaRO: Enhancing LLM Safety through Reasoning-based Alignment","created":"2025-04-13","cited_by_count":26,"area":"lr"},{"id":"2509.20357","title":"Language Models that Think, Chat Better","created":"2025-09-24","cited_by_count":24,"area":"lr"},{"id":"2502.03860","title":"BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation","created":"2025-02-06","cited_by_count":23,"area":"lr"},{"id":"2508.00410","title":"Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models","created":"2025-08-01","cited_by_count":23,"area":"lr"},{"id":"2509.26062","title":"DyFlow: Dynamic Workflow Framework for Agentic Reasoning","created":"2025-09-30","cited_by_count":23,"area":"lr"},{"id":"2510.00194","title":"GRPO-$\\lambda$: Credit Assignment improves LLM Reasoning","created":"2025-09-30","cited_by_count":23,"area":"lr"},{"id":"2504.18397","title":"Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization","created":"2025-04-25","cited_by_count":22,"area":"lr"},{"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":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2505.12366","title":"DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization","created":"2025-05-18","cited_by_count":16,"area":"lr"},{"id":"2501.13080","title":"Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment","created":"2025-01-22","cited_by_count":14,"area":"lr"},{"id":"2502.14356","title":"Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning","created":"2025-02-20","cited_by_count":14,"area":"lr"},{"id":"2505.07527","title":"Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning","created":"2025-05-12","cited_by_count":14,"area":"lr"},{"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":"2503.23513","title":"RARE: Retrieval-Augmented Reasoning Modeling","created":"2025-03-30","cited_by_count":11,"area":"lr"},{"id":"2505.15311","title":"Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning","created":"2025-05-21","cited_by_count":11,"area":"lr"},{"id":"2507.01551","title":"Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning","created":"2025-07-02","cited_by_count":11,"area":"lr"},{"id":"2512.22255","title":"Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks","created":"2025-12-24","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":"2509.16456","title":"GPO: Learning from Critical Steps to Improve LLM Reasoning","created":"2025-09-19","cited_by_count":10,"area":"lr"},{"id":"2603.13134","title":"When Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO","created":"2026-03-13","cited_by_count":10,"area":"lr"},{"id":"2502.11169","title":"CMCTS: A Constrained Monte Carlo Tree Search Framework for Mathematical Reasoning in Large Language Model","created":"2025-02-16","cited_by_count":9,"area":"lr"},{"id":"2502.11656","title":"Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL","created":"2025-02-17","cited_by_count":9,"area":"lr"},{"id":"2512.06337","title":"DaGRPO: Rectifying Gradient Conflict in Reasoning via Distinctiveness-Aware Group Relative Policy Optimization","created":"2025-12-06","cited_by_count":9,"area":"lr"},{"id":"2502.13173","title":"Thinking Preference Optimization","created":"2025-02-17","cited_by_count":8,"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":"2512.13159","title":"SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning","created":"2025-12-15","cited_by_count":8,"area":"lr"},{"id":"2605.19282","title":"Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR","created":"2026-05-19","cited_by_count":8,"area":"lr"},{"id":"2504.09802","title":"Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment","created":"2025-04-14","cited_by_count":7,"area":"lr"},{"id":"2603.09980","title":"Explainable LLM Unlearning Through Reasoning","created":"2026-02-08","cited_by_count":7,"area":"lr"},{"id":"2605.07331","title":"Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective","created":"2026-05-08","cited_by_count":7,"area":"lr"},{"id":"2406.16061","title":"PORT: Preference Optimization on Reasoning Traces","created":"2024-06-23","cited_by_count":6,"area":"lr"},{"id":"2505.15210","title":"Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs","created":"2025-05-21","cited_by_count":6,"area":"lr"},{"id":"2510.07038","title":"Tool-Augmented Policy Optimization: Synergizing Reasoning and Adaptive Tool Use with Reinforcement Learning","created":"2025-10-08","cited_by_count":6,"area":"lr"},{"id":"2503.03238","title":"FANS -- Formal Answer Selection for Natural Language Math Reasoning Using Lean4","created":"2025-03-05","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":"2504.09100","title":"A Short Survey on Small Reasoning Models: Training, Inference, Applications and Research Directions","created":"2025-04-12","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":"2510.09426","title":"KORMo: Korean Open Reasoning Model for Everyone","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2510.24794","title":"MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models","created":"2025-10-27","cited_by_count":4,"area":"lr"},{"id":"2510.26020","title":"PORTool: Importance-Aware Policy Optimization with Rewarded Tree for Multi-Tool-Integrated Reasoning","created":"2025-10-29","cited_by_count":4,"area":"lr"},{"id":"2604.08559","title":"Medical Reasoning with Large Language Models: A Survey and MR-Bench","created":"2026-03-17","cited_by_count":4,"area":"lr"},{"id":"2506.00845","title":"Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment","created":"2025-06-01","cited_by_count":3,"area":"lr"},{"id":"2506.08551","title":"DeepForm: Reasoning Large Language Model for Communication System Formulation","created":"2025-06-10","cited_by_count":3,"area":"lr"},{"id":"2506.13102","title":"Rethinking Test-Time Scaling for Medical AI: Model and Task-Aware Strategies for LLMs and VLMs","created":"2025-06-16","cited_by_count":3,"area":"lr"},{"id":"2509.23441","title":"Cognition-of-Thought Elicits Social-Aligned Reasoning in Large Language Models","created":"2025-09-27","cited_by_count":3,"area":"lr"},{"id":"2511.21638","title":"Iterative GRPO: Batch-Online Multi-Turn RL via Single-Turn RLHF","created":"2025-11-26","cited_by_count":3,"area":"lr"},{"id":"2605.12227","title":"A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and Distillation","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2407.08400","title":"Self-training Language Models for Arithmetic Reasoning","created":"2024-07-11","cited_by_count":2,"area":"lr"},{"id":"2505.19100","title":"ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning","created":"2025-05-25","cited_by_count":2,"area":"lr"},{"id":"2510.09211","title":"DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction","created":"2025-10-10","cited_by_count":2,"area":"lr"},{"id":"2510.17057","title":"The Ends Justify the Thoughts: RL-Induced Motivated Reasoning in LLM CoTs","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2512.17206","title":"Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs","created":"2025-12-19","cited_by_count":2,"area":"lr"},{"id":"2606.08543","title":"PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR","created":"2026-06-07","cited_by_count":2,"area":"lr"},{"id":"2406.08657","title":"Mistral-C2F: Coarse to Fine Actor for Analytical and Reasoning Enhancement in RLHF and Effective-Merged LLMs","created":"2024-06-12","cited_by_count":1,"area":"lr"},{"id":"2412.10566","title":"EVLM: Self-Reflective Multimodal Reasoning for Cross-Dimensional Visual Editing","created":"2024-12-13","cited_by_count":1,"area":"lr"},{"id":"2504.10647","title":"Improving In-Context Learning with Reasoning Distillation","created":"2025-04-14","cited_by_count":1,"area":"lr"},{"id":"2505.02142","title":"Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study","created":"2025-05-04","cited_by_count":1,"area":"lr"},{"id":"2601.12323","title":"MARO: Learning Stronger Reasoning from Social Interaction","created":"2026-01-18","cited_by_count":1,"area":"lr"},{"id":"2601.22230","title":"DAJ: Data-Reweighted LLM Judge for Test-Time Scaling in Code Generation","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2602.03084","title":"AERO: Autonomous Evolutionary Reasoning Optimization via Endogenous Dual-Loop Feedback","created":"2026-02-03","cited_by_count":1,"area":"lr"},{"id":"2602.07832","title":"rePIRL: Learn PRM with Inverse RL for LLM Reasoning","created":"2026-02-08","cited_by_count":1,"area":"lr"},{"id":"2604.25683","title":"K-CARE: Knowledge-driven Symmetrical Contextual Anchoring and Analogical Prototype Reasoning for E-commerce Relevance","created":"2026-04-28","cited_by_count":1,"area":"lr"},{"id":"2605.11906","title":"YFPO: Yoked Feature Preference Optimization with Neuron-Guided Rewards","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2605.27570","title":"LaneRoPE: Positional Encoding for Collaborative Parallel Reasoning and Generation","created":"2026-05-26","cited_by_count":1,"area":"lr"},{"id":"2505.06418","title":"Is your multimodal large language model a good science tutor?","created":"2025-05-09","cited_by_count":0,"area":"lr"},{"id":"2506.06009","title":"Unlocking Recursive Thinking of LLMs: Alignment via Refinement","created":"2025-06-06","cited_by_count":0,"area":"lr"},{"id":"2507.23170","title":"BAR Conjecture: the Feasibility of Inference Budget-Constrained LLM Services with Authenticity and Reasoning","created":"2025-07-31","cited_by_count":0,"area":"lr"},{"id":"2510.27462","title":"VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision","created":"2025-10-31","cited_by_count":0,"area":"lr"},{"id":"2511.12155","title":"Rethinking Deep Alignment Through The Lens Of Incomplete Learning","created":"2025-11-15","cited_by_count":0,"area":"lr"},{"id":"2601.13546","title":"ChatAD: Reasoning-Enhanced Time-Series Anomaly Detection with Multi-Turn Instruction Evolution","created":"2026-01-20","cited_by_count":0,"area":"lr"},{"id":"2602.01207","title":"Not All Preferences Deserve Gradients: Understanding Gradient Utility in Offline Reasoning Alignment","created":"2026-02-01","cited_by_count":0,"area":"lr"},{"id":"2602.04290","title":"Guided Verifier: Collaborative Multimodal Reasoning via Dynamic Process Supervision","created":"2026-02-04","cited_by_count":0,"area":"lr"},{"id":"2602.05946","title":"f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment","created":"2026-02-05","cited_by_count":0,"area":"lr"},{"id":"2604.17312","title":"A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2604.20140","title":"HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs","created":"2026-04-22","cited_by_count":0,"area":"lr"},{"id":"2605.11726","title":"Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.22358","title":"Integrating Chain-of-Thought into Generative Retrieval: A Preliminary Study","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2606.02981","title":"Predicting Inference-Time Scaling Gains from Labeled Validation-Set Output Statistics","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2606.24937","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2606.28707","title":"BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards","created":"2026-06-27","cited_by_count":0,"area":"lr"},{"id":"2607.18470","title":"RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2607.23075","title":"Traceable LLM Reasoning for Fake-Order Fraud Detection","created":"2026-07-25","cited_by_count":0,"area":"lr"},{"id":"2607.24833","title":"AdaKP: Online Adaptive Knowledge-Point Selection for Reasoning-Oriented Reinforcement Learning","created":"2026-07-23","cited_by_count":0,"area":"lr"},{"id":"2608.11674","title":"GCPO: Diagnosing and Constraining Subspace Geometry in Rollout RL for LLMs","created":"2026-08-12","cited_by_count":0,"area":"lr"},{"id":"2609.01658","title":"PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.15606","title":"VideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video Understanding","created":"2026-09-14","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}