{"total":242,"rows":[{"id":"2504.20571","title":"Reinforcement Learning for Reasoning in Large Language Models with One Training Example","created":"2025-04-29","cited_by_count":295,"area":"lr"},{"id":"2509.25140","title":"ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory","created":"2025-09-29","cited_by_count":284,"area":"lr"},{"id":"2509.02544","title":"UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning","created":"2025-09-02","cited_by_count":215,"area":"lr"},{"id":"2504.19678","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","created":"2025-04-28","cited_by_count":149,"area":"lr"},{"id":"2504.00050","title":"JudgeLRM: Large Reasoning Models as a Judge","created":"2025-03-31","cited_by_count":78,"area":"lr"},{"id":"2505.10320","title":"J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning","created":"2025-05-15","cited_by_count":75,"area":"lr"},{"id":"2505.21444","title":"Can Large Reasoning Models Self-Train?","created":"2025-05-27","cited_by_count":68,"area":"lr"},{"id":"2508.16949","title":"Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning","created":"2025-08-23","cited_by_count":63,"area":"lr"},{"id":"2507.22925","title":"Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents","created":"2025-07-23","cited_by_count":62,"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":"2510.23595","title":"Multi-Agent Evolve: LLM Self-Improve through Co-evolution","created":"2025-10-27","cited_by_count":60,"area":"lr"},{"id":"2504.10481","title":"xVerify: Efficient Answer Verifier for Reasoning Model Evaluations","created":"2025-04-14","cited_by_count":55,"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":"2504.02956","title":"Understanding Aha Moments: from External Observations to Internal Mechanisms","created":"2025-04-03","cited_by_count":50,"area":"lr"},{"id":"2505.14674","title":"Reward Reasoning Model","created":"2025-05-20","cited_by_count":47,"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":"2510.00915","title":"Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers","created":"2025-10-01","cited_by_count":45,"area":"lr"},{"id":"2505.13237","title":"SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information","created":"2025-05-19","cited_by_count":42,"area":"lr"},{"id":"2502.13383","title":"MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification","created":"2025-02-19","cited_by_count":39,"area":"lr"},{"id":"2506.10521","title":"Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning","created":"2025-06-12","cited_by_count":34,"area":"lr"},{"id":"2502.19918","title":"Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models","created":"2025-02-27","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":"2502.11569","title":"Towards Reasoning Ability of Small Language Models","created":"2025-02-17","cited_by_count":29,"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":"2509.26209","title":"Diversity-Incentivized Exploration for Versatile Reasoning","created":"2025-09-30","cited_by_count":28,"area":"lr"},{"id":"2506.09513","title":"ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning","created":"2025-06-11","cited_by_count":27,"area":"lr"},{"id":"2504.10337","title":"Heimdall: test-time scaling on the generative verification","created":"2025-04-14","cited_by_count":26,"area":"lr"},{"id":"2507.19227","title":"Jailbreaking Large Language Diffusion Models: Revealing Hidden Safety Flaws in Diffusion-Based Text Generation","created":"2025-07-25","cited_by_count":26,"area":"lr"},{"id":"2503.15707","title":"Safety Aware Task Planning via Large Language Models in Robotics","created":"2025-03-19","cited_by_count":24,"area":"lr"},{"id":"2510.12697","title":"Multi-Agent Debate for LLM Judges with Adaptive Stability Detection","created":"2025-10-14","cited_by_count":23,"area":"lr"},{"id":"2503.03746","title":"Process-based Self-Rewarding Language Models","created":"2025-03-05","cited_by_count":22,"area":"lr"},{"id":"2507.07988","title":"Automating Expert-Level Medical Reasoning Evaluation of Large Language Models","created":"2025-07-10","cited_by_count":22,"area":"lr"},{"id":"2505.14268","title":"Think-J: Learning to Think for Generative LLM-as-a-Judge","created":"2025-05-20","cited_by_count":21,"area":"lr"},{"id":"2506.17114","title":"Mathematical Proof as a Litmus Test: Revealing Failure Modes of Advanced Large Reasoning Models","created":"2025-06-20","cited_by_count":20,"area":"lr"},{"id":"2510.09720","title":"Preference-Aware Memory Update for Long-Term LLM Agents","created":"2025-10-10","cited_by_count":20,"area":"lr"},{"id":"2507.17842","title":"Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning","created":"2025-07-23","cited_by_count":19,"area":"lr"},{"id":"2508.13587","title":"Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation","created":"2025-08-19","cited_by_count":19,"area":"lr"},{"id":"2510.07300","title":"Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning","created":"2025-10-08","cited_by_count":18,"area":"lr"},{"id":"2511.13288","title":"Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO","created":"2025-11-17","cited_by_count":18,"area":"lr"},{"id":"2505.24238","title":"MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM","created":"2025-05-30","cited_by_count":17,"area":"lr"},{"id":"2509.23285","title":"Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning","created":"2025-09-27","cited_by_count":17,"area":"lr"},{"id":"2501.04671","title":"Retrieval-Based Interleaved Visual Chain-of-Thought in Real-World Driving Scenarios","created":"2025-01-08","cited_by_count":16,"area":"lr"},{"id":"2502.12583","title":"LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data","created":"2025-02-18","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":"2505.17267","title":"GreekBarBench: A Challenging Benchmark for Free-Text Legal Reasoning and Citations","created":"2025-05-22","cited_by_count":15,"area":"lr"},{"id":"2505.10937","title":"Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations","created":"2025-05-16","cited_by_count":14,"area":"lr"},{"id":"2505.17250","title":"ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models","created":"2025-05-22","cited_by_count":14,"area":"lr"},{"id":"2509.03059","title":"Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers","created":"2025-09-03","cited_by_count":14,"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":"2506.02532","title":"ReasoningFlow: Semantic Structure of Complex Reasoning Traces","created":"2025-06-03","cited_by_count":12,"area":"lr"},{"id":"2511.22134","title":"DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action","created":"2025-11-27","cited_by_count":12,"area":"lr"},{"id":"2602.02995","title":"Agent Alpha: Tree Search Unifying Generation, Exploration and Evaluation for Computer-Use Agents","created":"2026-02-03","cited_by_count":12,"area":"lr"},{"id":"2501.14431","title":"Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains","created":"2025-01-24","cited_by_count":11,"area":"lr"},{"id":"2507.23317","title":"Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner","created":"2025-07-31","cited_by_count":11,"area":"lr"},{"id":"2509.21823","title":"ProRe: A Proactive Reward System for GUI Agents via Reasoner-Actor Collaboration","created":"2025-09-26","cited_by_count":11,"area":"lr"},{"id":"2510.06036","title":"Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?","created":"2025-10-07","cited_by_count":11,"area":"lr"},{"id":"2510.11620","title":"Enhancing Long Chain-of-Thought Reasoning through Multi-Path Plan Aggregation","created":"2025-10-13","cited_by_count":11,"area":"lr"},{"id":"2602.04649","title":"Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models","created":"2026-02-04","cited_by_count":11,"area":"lr"},{"id":"2602.17053","title":"RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models","created":"2026-02-19","cited_by_count":11,"area":"lr"},{"id":"2503.01891","title":"MMSciBench: Benchmarking Language Models on Chinese Multimodal Scientific Problems","created":"2025-02-27","cited_by_count":10,"area":"lr"},{"id":"2504.00406","title":"VerifiAgent: a Unified Verification Agent in Language Model Reasoning","created":"2025-04-01","cited_by_count":10,"area":"lr"},{"id":"2505.08468","title":"Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?","created":"2025-05-13","cited_by_count":10,"area":"lr"},{"id":"2505.15110","title":"RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals","created":"2025-05-21","cited_by_count":10,"area":"lr"},{"id":"2506.15629","title":"Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability","created":"2025-06-18","cited_by_count":10,"area":"lr"},{"id":"2510.07243","title":"LeMAJ (Legal LLM-as-a-Judge): Bridging Legal Reasoning and LLM Evaluation","created":"2025-10-08","cited_by_count":10,"area":"lr"},{"id":"2502.11157","title":"Dyve: Thinking Fast and Slow for Dynamic Process Verification","created":"2025-02-16","cited_by_count":9,"area":"lr"},{"id":"2502.20196","title":"ChineseEcomQA: A Scalable E-commerce Concept Evaluation Benchmark for Large Language Models","created":"2025-02-27","cited_by_count":9,"area":"lr"},{"id":"2505.13346","title":"J4R: Learning to Judge with Equivalent Initial State Group Relative Policy Optimization","created":"2025-05-19","cited_by_count":9,"area":"lr"},{"id":"2509.21933","title":"Why Chain of Thought Fails in Clinical Text Understanding","created":"2025-09-26","cited_by_count":9,"area":"lr"},{"id":"2605.02913","title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","created":"2026-04-08","cited_by_count":9,"area":"lr"},{"id":"2412.11934","title":"Stepwise Reasoning Error Disruption Attack of LLMs","created":"2024-12-16","cited_by_count":8,"area":"lr"},{"id":"2506.00842","title":"Toward Structured Knowledge Reasoning: Contrastive Retrieval-Augmented Generation on Experience","created":"2025-06-01","cited_by_count":8,"area":"lr"},{"id":"2506.12509","title":"Graph of Verification: Structured Verification of LLM Reasoning with Directed Acyclic Graphs","created":"2025-06-14","cited_by_count":8,"area":"lr"},{"id":"2507.03133","title":"ReliableMath: Benchmark of Reliable Mathematical Reasoning on Large Language Models","created":"2025-07-03","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":"2510.03632","title":"MITS: Enhanced Tree Search Reasoning for LLMs via Pointwise Mutual Information","created":"2025-10-04","cited_by_count":8,"area":"lr"},{"id":"2510.10182","title":"A Survey of Inductive Reasoning for Large Language Models","created":"2025-10-11","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":"2603.03205","title":"Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use","created":"2026-03-03","cited_by_count":8,"area":"lr"},{"id":"2505.00875","title":"Thoughts without Thinking: Reconsidering the Explanatory Value of Chain-of-Thought Reasoning in LLMs through Agentic Pipelines","created":"2025-05-01","cited_by_count":7,"area":"lr"},{"id":"2505.17266","title":"Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2505.19690","title":"Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models","created":"2025-05-26","cited_by_count":7,"area":"lr"},{"id":"2508.01136","title":"DBAIOps: A Reasoning LLM-Enhanced Database Operation and Maintenance System using Knowledge Graphs","created":"2025-08-02","cited_by_count":7,"area":"lr"},{"id":"2508.15202","title":"Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models","created":"2025-08-21","cited_by_count":7,"area":"lr"},{"id":"2509.21871","title":"Unlocking the Essence of Beauty: Advanced Aesthetic Reasoning with Relative-Absolute Policy Optimization","created":"2025-09-26","cited_by_count":7,"area":"lr"},{"id":"2511.10621","title":"SSR: Socratic Self-Refine for Large Language Model Reasoning","created":"2025-11-13","cited_by_count":7,"area":"lr"},{"id":"2511.21667","title":"Escaping the Verifier: Learning to Reason via Demonstrations","created":"2025-11-26","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":"2601.14952","title":"CorpusQA: A 10 Million Token Benchmark for Corpus-Level Analysis and Reasoning","created":"2026-01-21","cited_by_count":7,"area":"lr"},{"id":"2603.05167","title":"C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning","created":"2026-03-05","cited_by_count":7,"area":"lr"},{"id":"2504.02670","title":"Affordable AI Assistants with Knowledge Graph of Thoughts","created":"2025-04-03","cited_by_count":6,"area":"lr"},{"id":"2505.03418","title":"Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey","created":"2025-05-06","cited_by_count":6,"area":"lr"},{"id":"2505.23449","title":"CMIE: Combining MLLM Insights with External Evidence for Explainable Out-of-Context Misinformation Detection","created":"2025-05-29","cited_by_count":6,"area":"lr"},{"id":"2506.08672","title":"RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling","created":"2025-06-10","cited_by_count":6,"area":"lr"},{"id":"2506.10903","title":"Beyond Gold Standards: Epistemic Ensemble of LLM Judges for Formal Mathematical Reasoning","created":"2025-06-12","cited_by_count":6,"area":"lr"},{"id":"2507.02145","title":"Reasoning or Not? A Comprehensive Evaluation of Reasoning LLMs for Dialogue Summarization","created":"2025-07-02","cited_by_count":6,"area":"lr"},{"id":"2508.02435","title":"Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking","created":"2025-08-04","cited_by_count":6,"area":"lr"},{"id":"2510.21285","title":"When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models","created":"2025-10-24","cited_by_count":6,"area":"lr"},{"id":"2511.14366","title":"ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning","created":"2025-11-18","cited_by_count":6,"area":"lr"},{"id":"2512.22631","title":"Evaluating GRPO and DPO for Faithful Chain-of-Thought Reasoning in LLMs","created":"2025-12-27","cited_by_count":6,"area":"lr"}],"next_cursor":"100"}