{"total":80,"rows":[{"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":"2503.20752","title":"Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models","created":"2025-03-26","cited_by_count":99,"area":"lr"},{"id":"2503.16252","title":"Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning","created":"2025-03-20","cited_by_count":83,"area":"lr"},{"id":"2504.20024","title":"SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning","created":"2025-04-28","cited_by_count":68,"area":"lr"},{"id":"2507.03019","title":"Look-Back: Implicit Visual Re-focusing in MLLM Reasoning","created":"2025-07-02","cited_by_count":55,"area":"lr"},{"id":"2505.20315","title":"Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL","created":"2025-05-22","cited_by_count":38,"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":"2503.22828","title":"Learning to Reason for Long-Form Story Generation","created":"2025-03-28","cited_by_count":34,"area":"lr"},{"id":"2506.04245","title":"Contextual Integrity in LLMs via Reasoning and Reinforcement Learning","created":"2025-05-29","cited_by_count":31,"area":"lr"},{"id":"2510.01624","title":"Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead","created":"2025-10-02","cited_by_count":28,"area":"lr"},{"id":"2505.13508","title":"Time-R1: Towards Comprehensive Temporal Reasoning in LLMs","created":"2025-05-16","cited_by_count":25,"area":"lr"},{"id":"2503.17979","title":"Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities","created":"2025-03-23","cited_by_count":20,"area":"lr"},{"id":"2504.14363","title":"Improving RL Exploration for LLM Reasoning through Retrospective Replay","created":"2025-04-19","cited_by_count":19,"area":"lr"},{"id":"2505.02665","title":"A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law","created":"2025-05-05","cited_by_count":19,"area":"lr"},{"id":"2505.24876","title":"Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks","created":"2025-05-30","cited_by_count":19,"area":"lr"},{"id":"2605.28014","title":"ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains","created":"2026-05-27","cited_by_count":17,"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":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2505.17534","title":"Co-Reinforcement Learning for Unified Multimodal Understanding and Generation","created":"2025-05-23","cited_by_count":15,"area":"lr"},{"id":"2505.13778","title":"CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs","created":"2025-05-19","cited_by_count":14,"area":"lr"},{"id":"2506.01748","title":"Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning","created":"2025-06-02","cited_by_count":14,"area":"lr"},{"id":"2506.12963","title":"Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills","created":"2025-06-15","cited_by_count":14,"area":"lr"},{"id":"2511.22645","title":"GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenes","created":"2025-11-27","cited_by_count":14,"area":"lr"},{"id":"2508.09804","title":"BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning","created":"2025-08-13","cited_by_count":13,"area":"lr"},{"id":"2506.18237","title":"AdapThink: Adaptive Thinking Preferences for Reasoning Language Model","created":"2025-06-23","cited_by_count":11,"area":"lr"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2504.10368","title":"Exploring the System 1 Thinking Capability of Large Reasoning Models","created":"2025-04-14","cited_by_count":10,"area":"lr"},{"id":"2506.04611","title":"Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning","created":"2025-06-05","cited_by_count":9,"area":"lr"},{"id":"2506.15211","title":"ProtoReasoning: Prototypes as the Foundation for Generalizable Reasoning in LLMs","created":"2025-06-18","cited_by_count":9,"area":"lr"},{"id":"2601.09215","title":"UserLM-R1: Modeling Human Reasoning in User Language Models with Multi-Reward Reinforcement Learning","created":"2026-01-14","cited_by_count":9,"area":"lr"},{"id":"2505.13973","title":"Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models","created":"2025-05-20","cited_by_count":8,"area":"lr"},{"id":"2510.05034","title":"Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models","created":"2025-10-06","cited_by_count":8,"area":"lr"},{"id":"2604.07165","title":"Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization","created":"2026-04-08","cited_by_count":8,"area":"lr"},{"id":"2505.11854","title":"Evaluating the Logical Reasoning Abilities of Large Reasoning Models","created":"2025-05-17","cited_by_count":7,"area":"lr"},{"id":"2505.19949","title":"Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions","created":"2025-05-26","cited_by_count":7,"area":"lr"},{"id":"2508.04848","title":"Large Language Models Reasoning Abilities Under Non-Ideal Conditions After RL-Fine-Tuning","created":"2025-08-06","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":"2504.02273","title":"Reasoning Under 1 Billion: Memory-Augmented Reinforcement Learning for Large Language Models","created":"2025-04-03","cited_by_count":6,"area":"lr"},{"id":"2507.00951","title":"Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impact","created":"2025-07-01","cited_by_count":6,"area":"lr"},{"id":"2508.05613","title":"Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models","created":"2025-08-07","cited_by_count":6,"area":"lr"},{"id":"2509.24375","title":"Reinforcement Mid-Training","created":"2025-09-29","cited_by_count":6,"area":"lr"},{"id":"2606.18967","title":"EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts","created":"2026-06-17","cited_by_count":6,"area":"lr"},{"id":"2506.11077","title":"CyclicReflex: Improving Reasoning Models via Cyclical Reflection Token Scheduling","created":"2025-06-04","cited_by_count":5,"area":"lr"},{"id":"2601.21484","title":"ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment","created":"2026-01-29","cited_by_count":5,"area":"lr"},{"id":"2505.17021","title":"ARB: A Comprehensive Arabic Multimodal Reasoning Benchmark","created":"2025-05-22","cited_by_count":4,"area":"lr"},{"id":"2506.07751","title":"AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking","created":"2025-06-09","cited_by_count":4,"area":"lr"},{"id":"2508.05015","title":"SPaCe: Unlocking Sample-Efficient Large Language Models Training With Self-Pace Curriculum Learning","created":"2025-08-07","cited_by_count":4,"area":"lr"},{"id":"2508.06412","title":"Sample-efficient LLM Optimization with Reset Replay","created":"2025-08-08","cited_by_count":4,"area":"lr"},{"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":"2511.11187","title":"ReTrace: Interactive Visualizations for Reasoning Traces of Large Reasoning Models","created":"2025-11-14","cited_by_count":3,"area":"lr"},{"id":"2512.13279","title":"AIR: Post-training Data Selection for Reasoning via Attention Head Influence","created":"2025-12-15","cited_by_count":3,"area":"lr"},{"id":"2602.19049","title":"IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning","created":"2026-02-22","cited_by_count":3,"area":"lr"},{"id":"2601.23032","title":"Guided by Trajectories: Repairing and Rewarding Tool-Use Trajectories for Tool-Integrated Reasoning","created":"2026-01-30","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":"2604.16557","title":"S-GRPO: Unified Post-Training for Large Vision-Language Models","created":"2026-04-17","cited_by_count":2,"area":"lr"},{"id":"2605.08817","title":"How You Begin is How You Reason: Driving Exploration in RLVR via Prefix-Tuned Priors","created":"2026-05-09","cited_by_count":2,"area":"lr"},{"id":"2606.09396","title":"PriFT: Prior-Support Guided Supervised Fine-Tuning","created":"2026-06-08","cited_by_count":2,"area":"lr"},{"id":"2606.13176","title":"Mental-R1: Aligning LLM Reasoning for Mental Health Assessment","created":"2026-06-11","cited_by_count":2,"area":"lr"},{"id":"2606.22938","title":"Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack Efficiently","created":"2026-06-22","cited_by_count":2,"area":"lr"},{"id":"2505.19848","title":"Improving Multilingual Math Reasoning for African Languages","created":"2025-05-26","cited_by_count":1,"area":"lr"},{"id":"2511.18261","title":"LLM Reasoning for Cold-Start Item Recommendation","created":"2025-11-23","cited_by_count":1,"area":"lr"},{"id":"2511.22854","title":"CRAwDAD: Causal Reasoning Augmentation with Dual-Agent Debate","created":"2025-11-28","cited_by_count":1,"area":"lr"},{"id":"2602.03547","title":"AffordanceGrasp-R1:Leveraging Reasoning-Based Affordance Segmentation with Reinforcement Learning for Robotic Grasping","created":"2026-02-03","cited_by_count":1,"area":"lr"},{"id":"2602.19069","title":"Asking the Right Questions: Improving Reasoning with Generated Stepping Stones","created":"2026-02-22","cited_by_count":1,"area":"lr"},{"id":"2603.06923","title":"Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping","created":"2026-03-06","cited_by_count":1,"area":"lr"},{"id":"2605.30861","title":"Distilling LLM Feedback for Lean Theorem Proving","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.06002","title":"Global-Local Monte Carlo Tree Search in Vision-Language Models for Text-to-3D Indoor Scene Generation","created":"2026-06-04","cited_by_count":1,"area":"lr"},{"id":"2504.19144","title":"ChiseLLM: Unleashing the Power of Reasoning LLMs for Chisel Agile Hardware Development","created":"2025-04-27","cited_by_count":0,"area":"lr"},{"id":"2508.10123","title":"Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts","created":"2025-08-13","cited_by_count":0,"area":"lr"},{"id":"2510.25310","title":"Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning","created":"2025-10-29","cited_by_count":0,"area":"lr"},{"id":"2601.18790","title":"MortalMATH: Evaluating the Conflict Between Reasoning Objectives and Emergency Contexts","created":"2026-01-26","cited_by_count":0,"area":"lr"},{"id":"2601.21909","title":"From Meta-Thought to Execution: Cognitively Aligned Post-Training for Generalizable and Reliable LLM Reasoning","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2603.14041","title":"GRPO and Reflection Reward for Mathematical Reasoning in Large Language Models","created":"2026-03-14","cited_by_count":0,"area":"lr"},{"id":"2604.10436","title":"SignReasoner: Compositional Reasoning for Complex Traffic Sign Understanding via Functional Structure Units","created":"2026-04-12","cited_by_count":0,"area":"lr"},{"id":"2605.20201","title":"Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2608.17055","title":"Wasted large language models: A life cycle thinking approach","created":"2026-08-17","cited_by_count":0,"area":"lr"},{"id":"2609.21432","title":"GVPO++: Group Variance Policy Optimization for LLM Post-Training and On-Policy Distillation","created":"2026-09-18","cited_by_count":0,"area":"lr"},{"id":"2609.25463","title":"Rollout Efficiency in Reinforcement Learning for Reasoning Large Language Models: A Taxonomy and Future Directions","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.30906","title":"ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement Learning","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2610.01936","title":"Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}