{"total":54,"rows":[{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341,"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":"2504.11456","title":"DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning","created":"2025-04-15","cited_by_count":280,"area":"lr"},{"id":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223,"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":"2507.20673","title":"Geometric-Mean Policy Optimization","created":"2025-07-28","cited_by_count":111,"area":"lr"},{"id":"2503.16219","title":"Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't","created":"2025-03-20","cited_by_count":74,"area":"lr"},{"id":"2507.16812","title":"MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning","created":"2025-07-22","cited_by_count":59,"area":"lr"},{"id":"2502.00334","title":"UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models","created":"2025-02-01","cited_by_count":48,"area":"lr"},{"id":"2505.05408","title":"Crosslingual Reasoning through Test-Time Scaling","created":"2025-05-08","cited_by_count":46,"area":"lr"},{"id":"2501.02448","title":"Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gap","created":"2025-01-05","cited_by_count":43,"area":"lr"},{"id":"2412.12881","title":"RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement","created":"2024-12-17","cited_by_count":40,"area":"lr"},{"id":"2501.02497","title":"A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning","created":"2025-01-05","cited_by_count":40,"area":"lr"},{"id":"2510.10649","title":"Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning","created":"2025-10-12","cited_by_count":34,"area":"lr"},{"id":"2505.16122","title":"Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Models","created":"2025-05-22","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":"2510.00977","title":"It Takes Two: Your GRPO Is Secretly DPO","created":"2025-10-01","cited_by_count":26,"area":"lr"},{"id":"2504.01995","title":"Brains vs. Bytes: Evaluating LLM Proficiency in Olympiad Mathematics","created":"2025-04-01","cited_by_count":24,"area":"lr"},{"id":"2506.08295","title":"From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?","created":"2025-06-09","cited_by_count":23,"area":"lr"},{"id":"2410.01428","title":"Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks","created":"2024-10-02","cited_by_count":22,"area":"lr"},{"id":"2407.07053","title":"Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model","created":"2024-07-09","cited_by_count":21,"area":"lr"},{"id":"2408.15778","title":"LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models","created":"2024-08-28","cited_by_count":19,"area":"lr"},{"id":"2505.16826","title":"KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning","created":"2025-05-22","cited_by_count":19,"area":"lr"},{"id":"2510.12171","title":"MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Science","created":"2025-10-14","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":"2501.13766","title":"UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language Models","created":"2025-01-23","cited_by_count":13,"area":"lr"},{"id":"2506.05295","title":"Sample Complexity and Representation Ability of Test-time Scaling Paradigms","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"id":"2602.03279","title":"Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis","created":"2026-02-03","cited_by_count":12,"area":"lr"},{"id":"2502.14333","title":"A Survey on Feedback-based Multi-step Reasoning for Large Language Models on Mathematics","created":"2025-02-20","cited_by_count":11,"area":"lr"},{"id":"2512.01274","title":"SUPERChem: A Multimodal Reasoning Benchmark in Chemistry","created":"2025-12-01","cited_by_count":9,"area":"lr"},{"id":"2501.11790","title":"Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables Questions","created":"2025-01-20","cited_by_count":7,"area":"lr"},{"id":"2506.01676","title":"K12Vista: Exploring the Boundaries of MLLMs in K-12 Education","created":"2025-06-02","cited_by_count":6,"area":"lr"},{"id":"2510.23027","title":"Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts","created":"2025-10-27","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":"2604.18584","title":"MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval","created":"2026-04-20","cited_by_count":6,"area":"lr"},{"id":"2503.06553","title":"ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges","created":"2025-03-09","cited_by_count":5,"area":"lr"},{"id":"2505.16031","title":"Children's Mental Models of AI Reasoning: Implications for AI Literacy Education","created":"2025-05-21","cited_by_count":5,"area":"lr"},{"id":"2411.06198","title":"OpenAI-o1 AB Testing: Does the o1 model really do good reasoning in math problem solving?","created":"2024-11-09","cited_by_count":4,"area":"lr"},{"id":"2504.16414","title":"Evaluating Multi-Hop Reasoning in Large Language Models: A Chemistry-Centric Case Study","created":"2025-04-23","cited_by_count":3,"area":"lr"},{"id":"2509.07711","title":"RIMO: An Easy-to-Evaluate, Hard-to-Solve Olympiad Benchmark for Advanced Mathematical Reasoning","created":"2025-09-09","cited_by_count":3,"area":"lr"},{"id":"2602.04620","title":"QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning","created":"2026-02-04","cited_by_count":3,"area":"lr"},{"id":"2410.20533","title":"Guiding Through Complexity: What Makes Good Supervision for Hard Math Reasoning Tasks?","created":"2024-10-27","cited_by_count":2,"area":"lr"},{"id":"2608.26070","title":"Prefix Sliding for efficient test-time scaling","created":"2026-08-26","cited_by_count":2,"area":"lr"},{"id":"2504.20771","title":"Computational Reasoning of Large Language Models","created":"2025-04-29","cited_by_count":1,"area":"lr"},{"id":"2601.19827","title":"When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering","created":"2026-01-27","cited_by_count":1,"area":"lr"},{"id":"2601.21936","title":"AgenticSimLaw: A Juvenile Courtroom Multi-Agent Debate Simulation for Explainable High-Stakes Tabular Decision Making","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2410.06638","title":"Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing","created":"2024-10-09","cited_by_count":0,"area":"lr"},{"id":"2602.05857","title":"BABE: Biology Arena BEnchmark","created":"2026-02-05","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":"2606.11470","title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2606.15872","title":"SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks","created":"2026-06-14","cited_by_count":0,"area":"lr"},{"id":"2608.30517","title":"ScienceArena: Benchmarking LLMs on Latest Scientific Olympiad Competitions","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.32235","title":"Solving Every Step Is Not Enough: Milestone Oracles Reveal a Composition Gap in LLM Math Reasoning","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2610.13996","title":"Splicing Hints into Reasoning Traces: Learning from Demonstrator Failures","created":"2026-09-26","cited_by_count":0,"area":"lr"}],"next_cursor":null}