{"total":1244,"rows":[{"id":"2505.05470","title":"Flow-GRPO: Training Flow Matching Models via Online RL","created":"2025-05-08","cited_by_count":661,"area":"lr"},{"id":"2501.12326","title":"UI-TARS: Pioneering Automated GUI Interaction with Native Agents","created":"2025-01-21","cited_by_count":610,"area":"agents"},{"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":"2505.22954","title":"Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents","created":"2025-05-29","cited_by_count":356,"area":"agents"},{"id":"2504.21801","title":"DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition","created":"2025-04-30","cited_by_count":287,"area":"lr"},{"id":"2504.02495","title":"Inference-Time Scaling for Generalist Reward Modeling","created":"2025-04-03","cited_by_count":239,"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":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2505.22312","title":"Skywork Open Reasoner 1 Technical Report","created":"2025-05-28","cited_by_count":165,"area":"lr"},{"id":"2605.00674","title":"Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs","created":"2026-05-01","cited_by_count":137,"area":null},{"id":"2502.07374","title":"LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!","created":"2025-02-11","cited_by_count":132,"area":"lr"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2503.17352","title":"OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles","created":"2025-03-21","cited_by_count":124,"area":"lr"},{"id":"2502.06807","title":"Competitive Programming with Large Reasoning Models","created":"2025-02-03","cited_by_count":119,"area":"lr"},{"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":"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":"2507.01925","title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","created":"2025-07-02","cited_by_count":96,"area":"vla"},{"id":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90,"area":"lr"},{"id":"2505.12346","title":"SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization","created":"2025-05-18","cited_by_count":89,"area":"lr"},{"id":"2507.06203","title":"A Survey on Latent Reasoning","created":"2025-07-08","cited_by_count":81,"area":"lr"},{"id":"2506.02355","title":"Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpening","created":"2025-06-03","cited_by_count":80,"area":"lr"},{"id":"2505.11821","title":"Reinforcing Multi-Turn Reasoning in LLM Agents via Fine-Grained Reward Structure and Credit Assignment","created":"2025-05-17","cited_by_count":79,"area":"lr"},{"id":"2506.21506","title":"Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge","created":"2025-06-26","cited_by_count":76,"area":"agents"},{"id":"2502.04128","title":"Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis","created":"2025-02-06","cited_by_count":70,"area":"lr"},{"id":"2502.18418","title":"Rank1: Test-Time Compute for Reranking in Information Retrieval","created":"2025-02-25","cited_by_count":70,"area":"lr"},{"id":"2505.21444","title":"Can Large Reasoning Models Self-Train?","created":"2025-05-27","cited_by_count":68,"area":"lr"},{"id":"2506.12928","title":"Scaling Test-time Compute for LLM Agents","created":"2025-06-15","cited_by_count":63,"area":"lr"},{"id":"2506.17211","title":"BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning","created":"2025-06-20","cited_by_count":63,"area":"lr"},{"id":"2510.16907","title":"VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents","created":"2025-10-19","cited_by_count":62,"area":"wm"},{"id":"2504.10081","title":"RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability","created":"2025-04-14","cited_by_count":59,"area":"lr"},{"id":"2505.08054","title":"FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning","created":"2025-05-12","cited_by_count":58,"area":"lr"},{"id":"2506.01713","title":"SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning","created":"2025-06-02","cited_by_count":57,"area":"lr"},{"id":"2506.17238","title":"Training a Scientific Reasoning Model for Chemistry","created":"2025-06-04","cited_by_count":56,"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":"2504.10342","title":"VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge","created":"2025-04-14","cited_by_count":55,"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":"2506.21277","title":"HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context","created":"2025-06-26","cited_by_count":55,"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":"2510.18855","title":"Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model","created":"2025-10-21","cited_by_count":55,"area":"lr"},{"id":"2505.10446","title":"Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models","created":"2025-05-15","cited_by_count":54,"area":"lr"},{"id":"2505.23575","title":"CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring","created":"2025-05-29","cited_by_count":54,"area":"lr"},{"id":"2507.04632","title":"Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?","created":"2025-07-07","cited_by_count":52,"area":"lr"},{"id":"2510.19807","title":"Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning","created":"2025-10-22","cited_by_count":52,"area":"lr"},{"id":"2503.18470","title":"MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse","created":"2025-03-24","cited_by_count":51,"area":"lr"},{"id":"2505.21297","title":"rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset","created":"2025-05-27","cited_by_count":51,"area":"lr"},{"id":"2504.15275","title":"Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning","created":"2025-04-21","cited_by_count":50,"area":"lr"},{"id":"2505.17667","title":"QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning","created":"2025-05-23","cited_by_count":50,"area":"lr"},{"id":"2507.14417","title":"Inverse Scaling in Test-Time Compute","created":"2025-07-19","cited_by_count":50,"area":"lr"},{"id":"2510.22319","title":"GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping","created":"2025-10-25","cited_by_count":49,"area":"lr"},{"id":"2505.02735","title":"FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models","created":"2025-05-05","cited_by_count":48,"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":"2505.14674","title":"Reward Reasoning Model","created":"2025-05-20","cited_by_count":47,"area":"lr"},{"id":"2506.18896","title":"ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs","created":"2025-06-23","cited_by_count":46,"area":"lr"},{"id":"2503.18866","title":"Reasoning to Learn from Latent Thoughts","created":"2025-03-24","cited_by_count":45,"area":"lr"},{"id":"2505.10557","title":"MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning","created":"2025-05-15","cited_by_count":45,"area":"lr"},{"id":"2503.16188","title":"Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning","created":"2025-03-20","cited_by_count":44,"area":"lr"},{"id":"2504.15253","title":"Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators","created":"2025-04-21","cited_by_count":44,"area":"lr"},{"id":"2504.04022","title":"Rethinking Reflection in Pre-Training","created":"2025-04-05","cited_by_count":43,"area":"lr"},{"id":"2508.13755","title":"Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration","created":"2025-08-19","cited_by_count":43,"area":"lr"},{"id":"2509.03646","title":"Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning","created":"2025-09-03","cited_by_count":42,"area":"lr"},{"id":"2505.22334","title":"Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start","created":"2025-05-28","cited_by_count":41,"area":"lr"},{"id":"2506.02208","title":"KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning","created":"2025-06-02","cited_by_count":41,"area":"lr"},{"id":"2507.21848","title":"EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity","created":"2025-07-29","cited_by_count":41,"area":"lr"},{"id":"2509.23045","title":"Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents","created":"2025-09-27","cited_by_count":41,"area":"agents"},{"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":"2505.15034","title":"RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning","created":"2025-05-21","cited_by_count":40,"area":"lr"},{"id":"2508.07629","title":"Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization","created":"2025-08-11","cited_by_count":39,"area":"lr"},{"id":"2504.03234","title":"Think When You Need: Self-Adaptive Chain-of-Thought Learning","created":"2025-04-04","cited_by_count":38,"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":"2506.18183","title":"Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?","created":"2025-06-22","cited_by_count":38,"area":"lr"},{"id":"2508.03440","title":"LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft Thinking","created":"2025-08-05","cited_by_count":38,"area":"lr"},{"id":"2508.13998","title":"Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation","created":"2025-08-19","cited_by_count":38,"area":"lr"},{"id":"2509.04475","title":"ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute","created":"2025-08-30","cited_by_count":38,"area":"lr"},{"id":"2509.23040","title":"Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents","created":"2025-09-27","cited_by_count":38,"area":"lr"},{"id":"2510.08049","title":"A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models","created":"2025-10-09","cited_by_count":38,"area":"lr"},{"id":"2502.17407","title":"Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning","created":"2025-02-24","cited_by_count":37,"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":"2505.14183","title":"ThinkSwitcher: When to Think Hard, When to Think Fast","created":"2025-05-20","cited_by_count":37,"area":"lr"},{"id":"2508.02120","title":"Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models","created":"2025-08-04","cited_by_count":37,"area":"lr"},{"id":"2502.08127","title":"Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance","created":"2025-02-12","cited_by_count":35,"area":"lr"},{"id":"2504.13367","title":"THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models","created":"2025-04-17","cited_by_count":35,"area":"lr"},{"id":"2505.11277","title":"Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning","created":"2025-05-16","cited_by_count":35,"area":"lr"},{"id":"2505.23648","title":"Continuous Chain of Thought Enables Parallel Exploration and Reasoning","created":"2025-05-29","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":"2509.26626","title":"Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models","created":"2025-09-30","cited_by_count":35,"area":"lr"},{"id":"2505.05315","title":"Scalable Chain of Thoughts via Elastic Reasoning","created":"2025-05-08","cited_by_count":34,"area":"lr"},{"id":"2505.16964","title":"MedFrameQA: A Multi-Image Medical VQA Benchmark for Clinical Reasoning","created":"2025-05-22","cited_by_count":34,"area":"lr"},{"id":"2505.22453","title":"First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training","created":"2025-05-28","cited_by_count":34,"area":"lr"},{"id":"2509.21128","title":"RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs","created":"2025-09-25","cited_by_count":34,"area":"lr"},{"id":"2505.04881","title":"ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning","created":"2025-05-08","cited_by_count":33,"area":"lr"},{"id":"2505.21327","title":"MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs","created":"2025-05-27","cited_by_count":33,"area":"lr"},{"id":"2507.06485","title":"Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning","created":"2025-07-09","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":"2503.13399","title":"MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research","created":"2025-03-17","cited_by_count":32,"area":"lr"},{"id":"2505.00681","title":"MINERVA: Evaluating Complex Video Reasoning","created":"2025-05-01","cited_by_count":32,"area":"lr"},{"id":"2506.01926","title":"Large language models can learn and generalize steganographic chain-of-thought under process supervision","created":"2025-06-02","cited_by_count":32,"area":"lr"},{"id":"2508.05988","title":"Pruning the Unsurprising: Efficient LLM Reasoning via First-Token Surprisal","created":"2025-08-08","cited_by_count":32,"area":"lr"},{"id":"2508.10433","title":"We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning","created":"2025-08-14","cited_by_count":32,"area":"lr"}],"next_cursor":"100"}