{"total":201,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820,"area":"lr"},{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567,"area":"agents"},{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497,"area":null},{"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":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","created":"2025-06-16","cited_by_count":263,"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":"2512.15745","title":"LLaDA2.0: Scaling Up Diffusion Language Models to 100B","created":"2025-12-10","cited_by_count":166,"area":"diffusion"},{"id":"2505.24760","title":"REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards","created":"2025-05-30","cited_by_count":130,"area":null},{"id":"2511.20347","title":"Soft Adaptive Policy Optimization","created":"2025-11-25","cited_by_count":96,"area":"lr"},{"id":"2504.05520","title":"Efficient Reinforcement Finetuning via Adaptive Curriculum Learning","created":"2025-04-07","cited_by_count":93,"area":"lr"},{"id":"2505.16400","title":"AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning","created":"2025-05-22","cited_by_count":87,"area":"lr"},{"id":"2506.14965","title":"Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective","created":"2025-06-17","cited_by_count":76,"area":"lr"},{"id":"2509.01322","title":"LongCat-Flash Technical Report","created":"2025-09-01","cited_by_count":58,"area":"agents"},{"id":"2505.19914","title":"Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles","created":"2025-05-26","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":"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":"2602.08676","title":"LLaDA2.1: Speeding Up Text Diffusion via Token Editing","created":"2026-02-09","cited_by_count":54,"area":"diffusion"},{"id":"2502.15652","title":"Empowering LLMs with Logical Reasoning: A Comprehensive Survey","created":"2025-02-21","cited_by_count":51,"area":"lr"},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2505.14615","title":"SATBench: Benchmarking LLMs' Logical Reasoning via Automated Puzzle Generation from SAT Formulas","created":"2025-05-20","cited_by_count":33,"area":"lr"},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"id":"2505.15431","title":"Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought","created":"2025-05-21","cited_by_count":29,"area":"lr"},{"id":"2511.00279","title":"LongCat-Flash-Omni Technical Report","created":"2025-10-31","cited_by_count":26,"area":"moe"},{"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":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"id":"2509.18883","title":"Introducing LongCat-Flash-Thinking: A Technical Report","created":"2025-09-23","cited_by_count":22,"area":"lr"},{"id":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"area":null},{"id":"2508.08636","title":"InternBootcamp: Boosting LLM Reasoning with Verifiable Task Scaling","created":"2025-08-12","cited_by_count":20,"area":"lr"},{"id":"2506.09853","title":"Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning","created":"2025-06-11","cited_by_count":17,"area":"lr"},{"id":"2507.17512","title":"Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning","created":"2025-07-23","cited_by_count":17,"area":"lr"},{"id":"2509.17325","title":"Generalizable End-to-End Tool-Use RL with Synthetic CodeGym","created":"2025-09-22","cited_by_count":17,"area":"agents"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2605.27115","title":"Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery with Domain Preservation","created":"2026-05-26","cited_by_count":15,"area":"distill"},{"id":"2505.17653","title":"GeoGramBench: Benchmarking the Geometric Program Reasoning in Modern LLMs","created":"2025-05-23","cited_by_count":13,"area":"lr"},{"id":"2505.21825","title":"Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones","created":"2025-05-27","cited_by_count":13,"area":"lr"},{"id":"2506.01341","title":"TurnBench-MS: A Benchmark for Evaluating Multi-Turn, Multi-Step Reasoning in Large Language Models","created":"2025-06-02","cited_by_count":13,"area":"lr"},{"id":"2507.00390","title":"MoNE: Replacing Redundant Experts with Lightweight Novices for Structured Pruning of MoE","created":"2025-07-01","cited_by_count":13,"area":"moe"},{"id":"2512.07461","title":"Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning","created":"2025-12-08","cited_by_count":12,"area":"lr"},{"id":"2601.20055","title":"VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning","created":"2026-01-27","cited_by_count":12,"area":"lr"},{"id":"2606.30626","title":"DOPD: Dual On-policy Distillation","created":"2026-06-29","cited_by_count":12,"area":"distill"},{"id":"2506.12241","title":"Privacy Reasoning in Ambiguous Contexts","created":"2025-06-13","cited_by_count":11,"area":"lr"},{"id":"2507.20527","title":"SAND-Math: Using LLMs to Generate Novel, Difficult and Useful Mathematics Questions and Answers","created":"2025-07-28","cited_by_count":11,"area":"lr"},{"id":"2510.16476","title":"NP-Engine: Empowering Optimization Reasoning in Large Language Models with Verifiable Synthetic NP Problems","created":"2025-10-18","cited_by_count":11,"area":"lr"},{"id":"2601.15593","title":"Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow","created":"2026-01-22","cited_by_count":11,"area":"diffusion"},{"id":"2602.04705","title":"ERNIE 5.0 Technical Report","created":"2026-02-04","cited_by_count":11,"area":"moe"},{"id":"2609.04108","title":"Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR","created":"2026-09-03","cited_by_count":11,"area":"lr"},{"id":"2510.07880","title":"Do LLMs Really Need 10+ Thoughts for \"Find the Time 1000 Days Later\"? Towards Structural Understanding of LLM Overthinking","created":"2025-10-09","cited_by_count":10,"area":"lr"},{"id":"2607.22529","title":"Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills","created":"2026-07-24","cited_by_count":10,"area":"synth"},{"id":"2602.02301","title":"Advancing General-Purpose Reasoning Models with Modular Gradient Surgery","created":"2026-02-02","cited_by_count":9,"area":"lr"},{"id":"2504.21303","title":"Confidence in Large Language Model Evaluation: A Bayesian Approach to Limited-Sample Challenges","created":"2025-04-30","cited_by_count":8,"area":null},{"id":"2510.02557","title":"Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge","created":"2025-10-02","cited_by_count":8,"area":"agents"},{"id":"2510.26143","title":"Reasoning Curriculum: Bootstrapping Broad LLM Reasoning from Math","created":"2025-10-30","cited_by_count":8,"area":"lr"},{"id":"2602.12413","title":"Soft Contamination Means Benchmarks Test Shallow Generalization","created":"2026-02-12","cited_by_count":8,"area":null},{"id":"2504.11239","title":"Nondeterministic Polynomial-time Problem Challenge: An Ever-Scaling Reasoning Benchmark for LLMs","created":"2025-04-15","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":"2507.17307","title":"R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning","created":"2025-07-23","cited_by_count":7,"area":"lr"},{"id":"2607.01763","title":"Denser $\\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training","created":"2026-07-02","cited_by_count":7,"area":"distill"},{"id":"2505.12151","title":"Reasoning Large Language Model Errors Arise from Hallucinating Critical Problem Features","created":"2025-05-17","cited_by_count":6,"area":"lr"},{"id":"2506.15787","title":"SLR: Automated Synthesis for Scalable Logical Reasoning","created":"2025-06-18","cited_by_count":6,"area":"lr"},{"id":"2510.01143","title":"Generalized Parallel Scaling with Interdependent Generations","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2510.09133","title":"On the Provable Performance Guarantee of Efficient Reasoning Models","created":"2025-10-10","cited_by_count":6,"area":"lr"},{"id":"2602.05843","title":"OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2606.15079","title":"Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale","created":"2026-06-13","cited_by_count":6,"area":"lr"},{"id":"2503.22832","title":"L0-Reasoning Bench: Evaluating Procedural Correctness in Language Models via Simple Program Execution","created":"2025-03-28","cited_by_count":5,"area":"lr"},{"id":"2506.04821","title":"LogicPuzzleRL: Cultivating Robust Mathematical Reasoning in LLMs via Reinforcement Learning","created":"2025-06-05","cited_by_count":5,"area":"lr"},{"id":"2509.06024","title":"Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL","created":"2025-09-07","cited_by_count":5,"area":"lr"},{"id":"2509.18083","title":"Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning","created":"2025-09-22","cited_by_count":5,"area":"lr"},{"id":"2512.00831","title":"ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning","created":"2025-11-30","cited_by_count":5,"area":"lr"},{"id":"2512.11143","title":"Automated Penetration Testing with LLM Agents and Classical Planning","created":"2025-12-11","cited_by_count":5,"area":"agents"},{"id":"2601.19924","title":"OPT-Engine: Benchmarking the Limits of LLMs in Optimization Modeling via Complexity Scaling","created":"2026-01-09","cited_by_count":5,"area":null},{"id":"2603.02119","title":"Pencil Puzzle Bench: A Benchmark for Multi-Step Verifiable Reasoning","created":"2026-03-02","cited_by_count":5,"area":"lr"},{"id":"2605.07579","title":"Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States","created":"2026-05-08","cited_by_count":5,"area":"lr"},{"id":"2606.25178","title":"Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2505.15712","title":"TurnaboutLLM: A Deductive Reasoning Benchmark from Detective Games","created":"2025-05-21","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":"2511.07464","title":"Motif 2 12.7B technical report","created":"2025-11-07","cited_by_count":4,"area":null},{"id":"2512.05065","title":"Personalizing Agent Privacy Decisions via Logical Entailment","created":"2025-12-04","cited_by_count":4,"area":"agents"},{"id":"2602.03978","title":"Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning","created":"2026-02-03","cited_by_count":4,"area":"lr"},{"id":"2602.10718","title":"SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2503.23487","title":"Large Language and Reasoning Models are Shallow Disjunctive Reasoners","created":"2025-03-30","cited_by_count":3,"area":"lr"},{"id":"2505.14763","title":"Unifying Inference-Time Planning Language Generation","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2507.07498","title":"Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code","created":"2025-07-10","cited_by_count":3,"area":"lr"},{"id":"2509.00930","title":"SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs","created":"2025-08-31","cited_by_count":3,"area":"lr"},{"id":"2509.18458","title":"CogniLoad: A Synthetic Natural Language Reasoning Benchmark With Tunable Length, Intrinsic Difficulty, and Distractor Density","created":"2025-09-22","cited_by_count":3,"area":"lr"},{"id":"2509.22504","title":"Estimating the Empowerment of Language Model Agents","created":"2025-09-26","cited_by_count":3,"area":"agents"},{"id":"2509.23962","title":"Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models","created":"2025-09-28","cited_by_count":3,"area":"lr"},{"id":"2509.24239","title":"ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models","created":"2025-09-29","cited_by_count":3,"area":"lr"},{"id":"2510.05486","title":"Language Model as Planner and Formalizer under Constraints","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2510.14581","title":"Model-agnostic Selective Labeling with Provable Statistical Guarantees","created":"2025-10-16","cited_by_count":3,"area":null},{"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":"2601.03550","title":"ReEfBench: Quantifying the Reasoning Efficiency of LLMs","created":"2026-01-07","cited_by_count":3,"area":"lr"},{"id":"2601.06160","title":"Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration","created":"2026-01-06","cited_by_count":3,"area":"lr"},{"id":"2602.06319","title":"Exposing Weaknesses of Large Reasoning Models through Graph Algorithm Problems","created":"2026-02-06","cited_by_count":3,"area":"lr"},{"id":"2604.03616","title":"The Format Tax","created":"2026-04-04","cited_by_count":3,"area":null},{"id":"2506.10527","title":"LogiPlan: A Structured Benchmark for Logical Planning and Relational Reasoning in LLMs","created":"2025-06-12","cited_by_count":2,"area":"lr"},{"id":"2506.15894","title":"Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning","created":"2025-06-18","cited_by_count":2,"area":"lr"},{"id":"2508.09125","title":"LogicIF: Towards Complex Logic Instruction Following","created":"2025-08-12","cited_by_count":2,"area":"agents"}],"next_cursor":"100"}