{"total":95,"rows":[{"id":"2412.21139","title":"Training Software Engineering Agents and Verifiers with SWE-Gym","created":"2024-12-30","cited_by_count":336,"area":"agents"},{"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":"2503.04472","title":"DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models","created":"2025-03-06","cited_by_count":158,"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":"2502.03275","title":"Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning","created":"2025-02-05","cited_by_count":91,"area":"lr"},{"id":"2502.19613","title":"Self-rewarding correction for mathematical reasoning","created":"2025-02-26","cited_by_count":70,"area":"lr"},{"id":"2409.02392","title":"Building Math Agents with Multi-Turn Iterative Preference Learning","created":"2024-09-04","cited_by_count":66,"area":"lr"},{"id":"2408.16737","title":"Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling","created":"2024-08-29","cited_by_count":61,"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":"2409.11704","title":"From Lists to Emojis: How Format Bias Affects Model Alignment","created":"2024-09-18","cited_by_count":49,"area":"alignment"},{"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":"2506.05183","title":"TreeRPO: Tree Relative Policy Optimization","created":"2025-06-05","cited_by_count":46,"area":"lr"},{"id":"2410.09918","title":"Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces","created":"2024-10-13","cited_by_count":43,"area":"lr"},{"id":"2506.08989","title":"SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning","created":"2025-06-10","cited_by_count":42,"area":"lr"},{"id":"2505.05464","title":"Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging","created":"2025-05-08","cited_by_count":40,"area":"lr"},{"id":"2412.11006","title":"Entropy-Regularized Process Reward Model","created":"2024-12-15","cited_by_count":38,"area":"lr"},{"id":"2409.12568","title":"InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning","created":"2024-09-19","cited_by_count":36,"area":"lr"},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"id":"2505.10833","title":"MergeBench: A Benchmark for Merging Domain-Specialized LLMs","created":"2025-05-16","cited_by_count":33,"area":null},{"id":"2501.11110","title":"Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective","created":"2025-01-19","cited_by_count":29,"area":"lr"},{"id":"2501.14275","title":"Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation","created":"2025-01-24","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":"2408.16326","title":"Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Critic","created":"2024-08-29","cited_by_count":28,"area":"lr"},{"id":"2503.08893","title":"EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees","created":"2025-03-11","cited_by_count":27,"area":null},{"id":"2509.11079","title":"Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflows","created":"2025-09-14","cited_by_count":27,"area":"agents"},{"id":"2412.17256","title":"B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners","created":"2024-12-23","cited_by_count":26,"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":"2505.02391","title":"Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL","created":"2025-05-05","cited_by_count":24,"area":"lr"},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2510.06672","title":"XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation","created":"2025-10-08","cited_by_count":18,"area":"lr"},{"id":"2507.07996","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","created":"2025-07-10","cited_by_count":16,"area":null},{"id":"2505.17063","title":"Synthetic Data RL: Task Definition Is All You Need","created":"2025-05-18","cited_by_count":15,"area":"lr"},{"id":"2510.04265","title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","created":"2025-10-05","cited_by_count":15,"area":"lr"},{"id":"2512.14051","title":"OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value","created":"2025-12-16","cited_by_count":15,"area":null},{"id":"2410.14208","title":"Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning","created":"2024-10-18","cited_by_count":13,"area":null},{"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":"2510.12773","title":"Dr.LLM: Dynamic Layer Routing in LLMs","created":"2025-10-14","cited_by_count":12,"area":null},{"id":"2502.06217","title":"Examining False Positives under Inference Scaling for Mathematical Reasoning","created":"2025-02-10","cited_by_count":11,"area":"lr"},{"id":"2508.04117","title":"Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks","created":"2025-08-06","cited_by_count":11,"area":"lr"},{"id":"2510.19099","title":"What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical Reasoning","created":"2025-10-21","cited_by_count":11,"area":"lr"},{"id":"2504.13145","title":"Exploring Expert Failures Improves LLM Agent Tuning","created":"2025-04-17","cited_by_count":9,"area":"agents"},{"id":"2606.06574","title":"Skip a Layer or Loop It? Learning Program-of-Layers in LLMs","created":"2026-06-04","cited_by_count":9,"area":null},{"id":"2511.22254","title":"Co-Evolving Agents: Learning from Failures as Hard Negatives","created":"2025-11-27","cited_by_count":8,"area":"agents"},{"id":"2410.01504","title":"PersonaMath: Boosting Mathematical Reasoning via Persona-Driven Data Augmentation","created":"2024-10-02","cited_by_count":7,"area":"lr"},{"id":"2410.16736","title":"Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration","created":"2024-10-22","cited_by_count":7,"area":"synth"},{"id":"2503.17195","title":"TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning","created":"2025-03-21","cited_by_count":7,"area":null},{"id":"2507.04391","title":"Does Learning Mathematical Problem-Solving Generalize to Broader Reasoning?","created":"2025-07-06","cited_by_count":7,"area":"lr"},{"id":"2510.17802","title":"Unbiased Gradient Low-Rank Projection","created":"2025-10-20","cited_by_count":7,"area":null},{"id":"2605.21801","title":"Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization","created":"2026-05-20","cited_by_count":7,"area":null},{"id":"2509.21070","title":"ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning","created":"2025-09-25","cited_by_count":6,"area":"lr"},{"id":"2510.10023","title":"Skill-Targeted Adaptive Training","created":"2025-10-11","cited_by_count":6,"area":null},{"id":"2602.12036","title":"Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models","created":"2026-02-12","cited_by_count":6,"area":null},{"id":"2406.14629","title":"Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study","created":"2024-06-20","cited_by_count":5,"area":"lr"},{"id":"2505.14999","title":"Learning to Rank Chain-of-Thought: Using a Small Model","created":"2025-05-21","cited_by_count":5,"area":"lr"},{"id":"2509.26226","title":"Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners","created":"2025-09-30","cited_by_count":5,"area":"lr"},{"id":"2412.17397","title":"Towards Intrinsic Self-Correction Enhancement in Monte Carlo Tree Search Boosted Reasoning via Iterative Preference Learning","created":"2024-12-23","cited_by_count":4,"area":"lr"},{"id":"2502.12022","title":"Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving","created":"2025-02-17","cited_by_count":4,"area":"lr"},{"id":"2506.06470","title":"SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation","created":"2025-06-06","cited_by_count":4,"area":"lr"},{"id":"2510.17715","title":"QueST: Incentivizing LLMs to Generate Difficult Problems","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2511.07368","title":"Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories","created":"2025-11-10","cited_by_count":4,"area":"lr"},{"id":"2511.07372","title":"Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training","created":"2025-11-10","cited_by_count":4,"area":"lr"},{"id":"2601.09733","title":"Closing the Data Loop: Using OpenDataArena to Engineer Superior Training Datasets","created":"2025-12-30","cited_by_count":4,"area":null},{"id":"2602.05943","title":"Orthogonal Model Merging","created":"2026-02-05","cited_by_count":4,"area":null},{"id":"2606.12594","title":"Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation","created":"2026-06-10","cited_by_count":4,"area":"lr"},{"id":"2608.05080","title":"Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning","created":"2026-08-05","cited_by_count":4,"area":null},{"id":"2412.04305","title":"ALMA: Alignment with Minimal Annotation","created":"2024-12-05","cited_by_count":3,"area":"alignment"},{"id":"2503.04167","title":"The Role of Visual Modality in Multimodal Mathematical Reasoning: Challenges and Insights","created":"2025-03-06","cited_by_count":3,"area":"lr"},{"id":"2503.23777","title":"CONGRAD:Conflicting Gradient Filtering for Multilingual Preference Alignment","created":"2025-03-31","cited_by_count":3,"area":"alignment"},{"id":"2509.25531","title":"MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources","created":"2025-09-29","cited_by_count":3,"area":"lr"},{"id":"2510.15050","title":"DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning","created":"2025-10-16","cited_by_count":3,"area":"lr"},{"id":"2410.13841","title":"A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2502.11573","title":"InfiR : Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning","created":"2025-02-17","cited_by_count":2,"area":"lr"},{"id":"2503.09730","title":"Local Look-Ahead Guidance via Verifier-in-the-Loop for Automated Theorem Proving","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2512.11470","title":"Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning","created":"2025-12-12","cited_by_count":2,"area":"lr"},{"id":"2602.00513","title":"Minerva: Reinforcement Learning with Verifiable Rewards for Cyber Threat Intelligence LLMs","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2510.21999","title":"Foundation of Intelligence: Review of Math Word Problems from Human Cognition Perspective","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2603.09184","title":"Latent-DARM: Bridging Discrete Diffusion And Autoregressive Models For Reasoning","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2603.29765","title":"Training-Free Dynamic Upcycling of Expert Language Models","created":"2026-03-31","cited_by_count":1,"area":"moe"},{"id":"2605.11611","title":"CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG","created":"2026-05-12","cited_by_count":1,"area":"rag"},{"id":"2605.18829","title":"Lossless Anti-Distillation Sampling","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2606.16501","title":"Post-Hoc Merging is Not Enough: Many-Shot Model Merging with Loss-Gap Balancing","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2607.11997","title":"Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2609.31360","title":"Programs-of-Layers in LLMs through the Lens of Cortical Areas","created":"2026-09-25","cited_by_count":1,"area":null},{"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":"2507.21166","title":"The Ratchet Effect in Silico: How Interaction Drives Cumulative Intelligence in Large Language Models","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2510.04617","title":"AdaR: A Framework for Equipping LLMs with Adaptive Reasoning","created":"2025-10-06","cited_by_count":0,"area":"lr"},{"id":"2510.26474","title":"Counteracting Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing","created":"2025-10-30","cited_by_count":0,"area":"lr"},{"id":"2602.19187","title":"Adaptive Problem Generation via Symbolic Representations","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2604.02715","title":"FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving","created":"2026-04-03","cited_by_count":0,"area":"moe"},{"id":"2605.20369","title":"DEL: Digit Entropy Loss for Numerical Learning of Large Language Models","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.10706","title":"Unifying Data, Memory, and Compute Efficiency in LLM training: A Survey","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2609.34184","title":"CASS: Contribution-Aware Structured Sparsity for Model Merging","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35793","title":"Learning from the Gap Between Pass@K and Pass@1","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.04751","title":"Dynamic Routing as a New Dimension for Test-time Versatility of LLMs","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.17607","title":"Facts Don't Speak Louder than Words: The Behavioral Essence of Long-CoT Distillation","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}