{"total":57,"rows":[{"id":"2503.21776","title":"Video-R1: Reinforcing Video Reasoning in MLLMs","created":"2025-03-27","cited_by_count":484,"area":"lr"},{"id":"2504.00050","title":"JudgeLRM: Large Reasoning Models as a Judge","created":"2025-03-31","cited_by_count":78,"area":"lr"},{"id":"2505.15117","title":"An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents","created":"2025-05-21","cited_by_count":46,"area":"lr"},{"id":"2505.11404","title":"Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner","created":"2025-05-16","cited_by_count":40,"area":"lr"},{"id":"2505.24183","title":"QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation","created":"2025-05-30","cited_by_count":35,"area":"lr"},{"id":"2506.16395","title":"OJBench: A Competition Level Code Benchmark For Large Language Models","created":"2025-06-19","cited_by_count":26,"area":"lr"},{"id":"2504.15716","title":"DianJin-R1: Evaluating and Enhancing Financial Reasoning in Large Language Models","created":"2025-04-22","cited_by_count":22,"area":"lr"},{"id":"2511.06499","title":"SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sports","created":"2025-11-09","cited_by_count":17,"area":"lr"},{"id":"2508.04440","title":"StepFun-Formalizer: Unlocking the Autoformalization Potential of LLMs through Knowledge-Reasoning Fusion","created":"2025-08-06","cited_by_count":16,"area":"lr"},{"id":"2506.02515","title":"FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning","created":"2025-06-03","cited_by_count":15,"area":"lr"},{"id":"2506.09790","title":"ComfyUI-R1: Exploring Reasoning Models for Workflow Generation","created":"2025-06-11","cited_by_count":15,"area":"lr"},{"id":"2509.11420","title":"Trading-R1: Financial Trading with LLM Reasoning via Reinforcement Learning","created":"2025-09-14","cited_by_count":15,"area":"lr"},{"id":"2508.02066","title":"MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs","created":"2025-08-04","cited_by_count":12,"area":"lr"},{"id":"2510.10072","title":"Unilaw-R1: A Large Language Model for Legal Reasoning with Reinforcement Learning and Iterative Inference","created":"2025-10-11","cited_by_count":12,"area":"lr"},{"id":"2509.24193","title":"AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2505.17244","title":"ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models","created":"2025-05-22","cited_by_count":9,"area":"lr"},{"id":"2506.07104","title":"How Far Are We from Optimal Reasoning Efficiency?","created":"2025-06-08","cited_by_count":8,"area":"lr"},{"id":"2512.23515","title":"Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning","created":"2025-12-29","cited_by_count":7,"area":"lr"},{"id":"2506.04574","title":"Reasoning or Overthinking: Evaluating Large Language Models on Financial Sentiment Analysis","created":"2025-06-05","cited_by_count":6,"area":"lr"},{"id":"2507.16802","title":"Agentar-Fin-R1: Enhancing Financial Intelligence through Domain Expertise, Training Efficiency, and Advanced Reasoning","created":"2025-07-22","cited_by_count":6,"area":"lr"},{"id":"2604.06156","title":"MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control","created":"2026-04-07","cited_by_count":6,"area":"lr"},{"id":"2506.16123","title":"FinCoT: Grounding Chain-of-Thought in Expert Financial Reasoning","created":"2025-06-19","cited_by_count":5,"area":"lr"},{"id":"2511.08616","title":"Reasoning on Time-Series for Financial Technical Analysis","created":"2025-11-06","cited_by_count":5,"area":"lr"},{"id":"2511.12908","title":"DeepSport: A Multimodal Large Language Model for Comprehensive Sports Video Reasoning via Agentic Reinforcement Learning","created":"2025-11-17","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":"2605.03460","title":"FinSTaR: Towards Financial Reasoning with Time Series Reasoning Models","created":"2026-05-05","cited_by_count":4,"area":"lr"},{"id":"2507.01327","title":"Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy","created":"2025-07-02","cited_by_count":3,"area":"lr"},{"id":"2509.25987","title":"R-Log: Incentivizing Log Analysis Capability in LLMs via Reasoning-based Reinforcement Learning","created":"2025-09-30","cited_by_count":3,"area":"lr"},{"id":"2603.29232","title":"Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs","created":"2026-03-31","cited_by_count":3,"area":"lr"},{"id":"2604.28005","title":"Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning","created":"2026-04-30","cited_by_count":3,"area":"lr"},{"id":"2506.00577","title":"Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs","created":"2025-05-31","cited_by_count":2,"area":"lr"},{"id":"2506.13066","title":"FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design","created":"2025-06-16","cited_by_count":2,"area":"lr"},{"id":"2506.21591","title":"FinEval-KR: A Financial Domain Evaluation Framework for Large Language Models' Knowledge and Reasoning","created":"2025-06-18","cited_by_count":2,"area":"lr"},{"id":"2601.01195","title":"Reinforcement Learning Enhanced Multi-hop Reasoning for Temporal Knowledge Question Answering","created":"2026-01-03","cited_by_count":2,"area":"lr"},{"id":"2601.16447","title":"Mixing Expert Knowledge: Bring Human Thoughts Back To the Game of Go","created":"2026-01-23","cited_by_count":2,"area":"lr"},{"id":"2602.12113","title":"Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2505.18467","title":"Pedagogy-R1: Pedagogically-Aligned Reasoning Model with Balanced Educational Benchmark","created":"2025-05-24","cited_by_count":1,"area":"lr"},{"id":"2507.06057","title":"FEVO: Financial Knowledge Expansion and Reasoning Evolution for Large Language Models","created":"2025-07-08","cited_by_count":1,"area":"lr"},{"id":"2509.09942","title":"Towards Secure and Explainable Smart Contract Generation with Security-Aware Group Relative Policy Optimization","created":"2025-09-12","cited_by_count":1,"area":"lr"},{"id":"2509.14180","title":"Synthesizing Behaviorally-Grounded Reasoning Chains: A Data-Generation Framework for Personal Finance LLMs","created":"2025-09-17","cited_by_count":1,"area":"lr"},{"id":"2510.21604","title":"RETuning: Upgrading Inference-Time Scaling for Stock Movement Prediction with Large Language Models","created":"2025-10-24","cited_by_count":1,"area":"lr"},{"id":"2601.04853","title":"RAAR: Retrieval Augmented Agentic Reasoning for Cross-Domain Misinformation Detection","created":"2026-01-08","cited_by_count":1,"area":"lr"},{"id":"2602.17072","title":"BankMathBench: A Benchmark for Numerical Reasoning in Banking Scenarios","created":"2026-02-19","cited_by_count":1,"area":"lr"},{"id":"2603.19254","title":"FinReasoning: A Hierarchical Benchmark for Reliable Financial Research Reporting","created":"2026-02-25","cited_by_count":1,"area":"lr"},{"id":"2605.21975","title":"Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs","created":"2026-05-21","cited_by_count":1,"area":"lr"},{"id":"2605.27293","title":"BASIS: Batchwise Advantage Estimation from Single-Rollout Information Sharing for LLM Reasoning","created":"2026-05-26","cited_by_count":1,"area":"lr"},{"id":"2606.17642","title":"FinAcumen: Financial Multimodal Reasoning via Self-Evolving Experience Memory Harness","created":"2026-06-16","cited_by_count":1,"area":"lr"},{"id":"2601.07754","title":"Structure First, Reason Next: Enhancing a Large Language Model using Knowledge Graph for Numerical Reasoning in Financial Documents","created":"2026-01-12","cited_by_count":0,"area":"lr"},{"id":"2601.18582","title":"From Classification to Ranking: Enhancing LLM Reasoning Capabilities for MBTI Personality Detection","created":"2026-01-26","cited_by_count":0,"area":"lr"},{"id":"2605.00257","title":"Retrieval-Augmented Reasoning for Chartered Accountancy","created":"2026-04-30","cited_by_count":0,"area":"lr"},{"id":"2605.02933","title":"Relation Reasoning with LLMs in Expensive Optimization","created":"2026-04-30","cited_by_count":0,"area":"lr"},{"id":"2605.04499","title":"Pen-Strategist: A Reasoning Framework for Penetration Testing Strategy Formation and Analysis","created":"2026-05-06","cited_by_count":0,"area":"lr"},{"id":"2605.25281","title":"READER: Reasoning-Enhanced AI-Generated Text Detection","created":"2026-05-24","cited_by_count":0,"area":"lr"},{"id":"2606.01145","title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","created":"2026-05-31","cited_by_count":0,"area":"lr"},{"id":"2607.28661","title":"Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements","created":"2026-07-22","cited_by_count":0,"area":"lr"},{"id":"2608.28402","title":"VERA-8B: Evidence-Grounded Audit Risk Reasoning from SEC Filings","created":"2026-08-28","cited_by_count":0,"area":"lr"},{"id":"2609.10113","title":"Data-Centric Post-Training for Financial Reasoning: Mining, Distillation, and Verifiable Learning","created":"2026-09-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}