{"total":320,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820,"area":"lr"},{"id":"2503.01785","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","created":"2025-03-03","cited_by_count":513,"area":"lr"},{"id":"2503.24290","title":"Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model","created":"2025-03-31","cited_by_count":461,"area":"lr"},{"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":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344,"area":"lr"},{"id":"2504.21776","title":"WebThinker: Empowering Large Reasoning Models with Deep Research Capability","created":"2025-04-30","cited_by_count":335,"area":"lr"},{"id":"2412.06559","title":"ProcessBench: Identifying Process Errors in Mathematical Reasoning","created":"2024-12-09","cited_by_count":292,"area":"lr"},{"id":"2505.24298","title":"AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning","created":"2025-05-30","cited_by_count":250,"area":"lr"},{"id":"2506.17298","title":"Mercury: Ultra-Fast Language Models Based on Diffusion","created":"2025-06-17","cited_by_count":235,"area":"lr"},{"id":"2507.01352","title":"Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy","created":"2025-07-02","cited_by_count":214,"area":"lr"},{"id":"2502.18581","title":"Scalable Best-of-N Selection for Large Language Models via Self-Certainty","created":"2025-02-25","cited_by_count":187,"area":"lr"},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2503.02951","title":"KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding","created":"2025-03-04","cited_by_count":119,"area":"lr"},{"id":"2504.16828","title":"Process Reward Models That Think","created":"2025-04-23","cited_by_count":118,"area":"lr"},{"id":"2501.01257","title":"CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings","created":"2025-01-02","cited_by_count":115,"area":"lr"},{"id":"2504.01943","title":"OpenCodeReasoning: Advancing Data Distillation for Competitive Coding","created":"2025-04-02","cited_by_count":113,"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":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"area":"lr"},{"id":"2502.14382","title":"S*: Test Time Scaling for Code Generation","created":"2025-02-20","cited_by_count":98,"area":"lr"},{"id":"2503.02318","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","created":"2025-03-04","cited_by_count":95,"area":"lr"},{"id":"2508.11408","title":"On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting","created":"2025-08-15","cited_by_count":91,"area":"lr"},{"id":"2505.03318","title":"Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning","created":"2025-05-06","cited_by_count":90,"area":"lr"},{"id":"2505.14231","title":"UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning","created":"2025-05-20","cited_by_count":84,"area":"lr"},{"id":"2508.13167","title":"Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL","created":"2025-08-06","cited_by_count":80,"area":"lr"},{"id":"2503.09501","title":"ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning","created":"2025-03-12","cited_by_count":79,"area":"lr"},{"id":"2412.15084","title":"AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling","created":"2024-12-19","cited_by_count":77,"area":"lr"},{"id":"2506.13284","title":"AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy","created":"2025-06-16","cited_by_count":77,"area":"lr"},{"id":"2504.14655","title":"LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs","created":"2025-04-20","cited_by_count":70,"area":"lr"},{"id":"2504.09641","title":"TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning","created":"2025-04-13","cited_by_count":62,"area":"lr"},{"id":"2506.16499","title":"ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning","created":"2025-06-19","cited_by_count":61,"area":"lr"},{"id":"2503.23157","title":"Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL","created":"2025-03-29","cited_by_count":59,"area":"lr"},{"id":"2509.14279","title":"Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization","created":"2025-09-16","cited_by_count":56,"area":"lr"},{"id":"2502.07316","title":"CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction","created":"2025-02-11","cited_by_count":55,"area":"lr"},{"id":"2501.14723","title":"CodeMonkeys: Scaling Test-Time Compute for Software Engineering","created":"2025-01-24","cited_by_count":51,"area":"lr"},{"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":"2504.02807","title":"MegaMath: Pushing the Limits of Open Math Corpora","created":"2025-04-03","cited_by_count":51,"area":"lr"},{"id":"2504.12522","title":"Evaluating the Diversity and Quality of LLM Generated Content","created":"2025-04-16","cited_by_count":51,"area":"lr"},{"id":"2505.20347","title":"SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data","created":"2025-05-25","cited_by_count":51,"area":"lr"},{"id":"2412.14135","title":"Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective","created":"2024-12-18","cited_by_count":50,"area":"lr"},{"id":"2505.21318","title":"Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations","created":"2025-05-27","cited_by_count":49,"area":"lr"},{"id":"2502.19411","title":"Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs","created":"2025-02-26","cited_by_count":47,"area":"lr"},{"id":"2505.17612","title":"Distilling LLM Agent into Small Models with Retrieval and Code Tools","created":"2025-05-23","cited_by_count":47,"area":"lr"},{"id":"2505.23752","title":"ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks","created":"2025-05-29","cited_by_count":46,"area":"lr"},{"id":"2502.03492","title":"Teaching Language Models to Critique via Reinforcement Learning","created":"2025-02-05","cited_by_count":42,"area":"lr"},{"id":"2411.16345","title":"Preference Optimization for Reasoning with Pseudo Feedback","created":"2024-11-25","cited_by_count":39,"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":"2505.12415","title":"Table-R1: Region-based Reinforcement Learning for Table Understanding","created":"2025-05-18","cited_by_count":37,"area":"lr"},{"id":"2504.00810","title":"Z1: Efficient Test-time Scaling with Code","created":"2025-04-01","cited_by_count":35,"area":"lr"},{"id":"2505.24183","title":"QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation","created":"2025-05-30","cited_by_count":35,"area":"lr"},{"id":"2602.22495","title":"Reinforcement-aware Knowledge Distillation for LLM Reasoning","created":"2026-02-26","cited_by_count":35,"area":"lr"},{"id":"2507.05255","title":"Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning","created":"2025-07-07","cited_by_count":34,"area":"lr"},{"id":"2502.02871","title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","created":"2025-02-05","cited_by_count":33,"area":"lr"},{"id":"2502.05234","title":"Optimizing Temperature for Language Models with Multi-Sample Inference","created":"2025-02-07","cited_by_count":33,"area":"lr"},{"id":"2502.12468","title":"MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation","created":"2025-02-18","cited_by_count":32,"area":"lr"},{"id":"2503.15341","title":"Uncertainty-Guided Chain-of-Thought for Code Generation with LLMs","created":"2025-03-19","cited_by_count":32,"area":"lr"},{"id":"2504.09772","title":"Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning","created":"2025-04-14","cited_by_count":29,"area":"lr"},{"id":"2508.17196","title":"BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens","created":"2025-08-24","cited_by_count":29,"area":"lr"},{"id":"2510.04573","title":"LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning","created":"2025-10-06","cited_by_count":29,"area":"lr"},{"id":"2502.20127","title":"SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning","created":"2025-02-27","cited_by_count":28,"area":"lr"},{"id":"2504.06122","title":"Leanabell-Prover: Posttraining Scaling in Formal Reasoning","created":"2025-04-08","cited_by_count":27,"area":"lr"},{"id":"2503.23803","title":"Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute","created":"2025-03-31","cited_by_count":26,"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":"2512.15489","title":"Nemotron-Math: Efficient Long-Context Distillation of Mathematical Reasoning from Multi-Mode Supervision","created":"2025-12-17","cited_by_count":26,"area":"lr"},{"id":"2508.12800","title":"Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward","created":"2025-08-18","cited_by_count":25,"area":"lr"},{"id":"2510.13554","title":"Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization","created":"2025-10-15","cited_by_count":25,"area":"lr"},{"id":"2601.04171","title":"Agentic Rubrics as Contextual Verifiers for SWE Agents","created":"2026-01-07","cited_by_count":25,"area":"lr"},{"id":"2410.18693","title":"Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch","created":"2024-10-24","cited_by_count":24,"area":"lr"},{"id":"2503.19988","title":"ExCoT: Optimizing Reasoning for Text-to-SQL with Execution Feedback","created":"2025-03-25","cited_by_count":24,"area":"lr"},{"id":"2507.05418","title":"Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning","created":"2025-07-07","cited_by_count":24,"area":"lr"},{"id":"2509.24403","title":"Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling","created":"2025-09-29","cited_by_count":24,"area":"lr"},{"id":"2502.14361","title":"Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning","created":"2025-02-20","cited_by_count":23,"area":"lr"},{"id":"2506.04405","title":"MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science","created":"2025-06-04","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":"2506.05566","title":"ScaleRTL: Scaling LLMs with Reasoning Data and Test-Time Compute for Accurate RTL Code Generation","created":"2025-06-05","cited_by_count":22,"area":"lr"},{"id":"2412.15118","title":"Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation","created":"2024-12-19","cited_by_count":21,"area":"lr"},{"id":"2506.07927","title":"Solving Inequality Proofs with Large Language Models","created":"2025-06-09","cited_by_count":21,"area":"lr"},{"id":"2410.12381","title":"HumanEval-V: Benchmarking High-Level Visual Reasoning with Complex Diagrams in Coding Tasks","created":"2024-10-16","cited_by_count":20,"area":"lr"},{"id":"2507.21990","title":"ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge","created":"2025-07-29","cited_by_count":20,"area":"lr"},{"id":"2511.20100","title":"QiMeng-Kernel: Macro-Thinking Micro-Coding Paradigm for LLM-Based High-Performance GPU Kernel Generation","created":"2025-11-25","cited_by_count":19,"area":"lr"},{"id":"2410.01999","title":"CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs","created":"2024-10-02","cited_by_count":18,"area":"lr"},{"id":"2501.16207","title":"From Informal to Formal -- Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs","created":"2025-01-27","cited_by_count":18,"area":"lr"},{"id":"2506.01710","title":"Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning","created":"2025-06-02","cited_by_count":18,"area":"lr"},{"id":"2507.19060","title":"PurpCode: Reasoning for Safer Code Generation","created":"2025-07-25","cited_by_count":18,"area":"lr"},{"id":"2510.11369","title":"Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment","created":"2025-10-13","cited_by_count":18,"area":"lr"},{"id":"2505.23604","title":"Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering","created":"2025-05-29","cited_by_count":17,"area":"lr"},{"id":"2509.23808","title":"Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoning","created":"2025-09-28","cited_by_count":17,"area":"lr"},{"id":"2503.04779","title":"Can LLMs Reason About Program Semantics? A Comprehensive Evaluation of LLMs on Formal Specification Inference","created":"2025-02-22","cited_by_count":16,"area":"lr"},{"id":"2504.20708","title":"Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think","created":"2025-04-29","cited_by_count":16,"area":"lr"},{"id":"2507.06181","title":"CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization","created":"2025-07-08","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":"2506.09790","title":"ComfyUI-R1: Exploring Reasoning Models for Workflow Generation","created":"2025-06-11","cited_by_count":15,"area":"lr"},{"id":"2506.10446","title":"Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty","created":"2025-06-12","cited_by_count":15,"area":"lr"},{"id":"2508.03012","title":"Tool-integrated Reinforcement Learning for Repo Deep Search","created":"2025-08-05","cited_by_count":15,"area":"lr"},{"id":"2509.22644","title":"WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning","created":"2025-09-26","cited_by_count":15,"area":"lr"},{"id":"2502.16614","title":"CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Models","created":"2025-02-23","cited_by_count":14,"area":"lr"},{"id":"2504.14119","title":"CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning","created":"2025-04-19","cited_by_count":14,"area":"lr"},{"id":"2504.15077","title":"Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL","created":"2025-04-21","cited_by_count":14,"area":"lr"},{"id":"2505.18700","title":"GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains","created":"2025-05-24","cited_by_count":14,"area":"lr"},{"id":"2507.06920","title":"Rethinking Verification for LLM Code Generation: From Generation to Testing","created":"2025-07-09","cited_by_count":14,"area":"lr"},{"id":"2508.14313","title":"AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning","created":"2025-08-19","cited_by_count":14,"area":"lr"}],"next_cursor":"100"}