{"total":61,"rows":[{"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":"2410.01560","title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","created":"2024-10-02","cited_by_count":200,"area":"lr"},{"id":"2505.16839","title":"LaViDa: A Large Diffusion Language Model for Multimodal Understanding","created":"2025-05-22","cited_by_count":84,"area":"lr"},{"id":"2511.08325","title":"AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress","created":"2025-11-11","cited_by_count":77,"area":"lr"},{"id":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","cited_by_count":52,"area":"lr"},{"id":"2504.13171","title":"Sleep-time Compute: Beyond Inference Scaling at Test-time","created":"2025-04-17","cited_by_count":43,"area":"lr"},{"id":"2504.01005","title":"When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning","created":"2025-04-01","cited_by_count":42,"area":"lr"},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2410.05318","title":"Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification","created":"2024-10-05","cited_by_count":40,"area":"lr"},{"id":"2410.16377","title":"A Simple Model of Inference Scaling Laws","created":"2024-10-21","cited_by_count":36,"area":null},{"id":"2501.01054","title":"Dynamic Scaling of Unit Tests for Code Reward Modeling","created":"2025-01-02","cited_by_count":33,"area":"lr"},{"id":"2502.01612","title":"Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges","created":"2025-02-03","cited_by_count":31,"area":"synth"},{"id":"2410.01748","title":"Not All LLM Reasoners Are Created Equal","created":"2024-10-02","cited_by_count":30,"area":"lr"},{"id":"2505.09561","title":"Learning Long-Context Diffusion Policies via Past-Token Prediction","created":"2025-05-14","cited_by_count":30,"area":"diffusion"},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"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":"2410.01769","title":"Quantifying Generalization Complexity for Large Language Models","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2412.02674","title":"Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models","created":"2024-12-03","cited_by_count":18,"area":"synth"},{"id":"2503.02103","title":"Superficial Self-Improved Reasoners Benefit from Model Merging","created":"2025-03-03","cited_by_count":16,"area":"lr"},{"id":"2409.19759","title":"Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs","created":"2024-09-29","cited_by_count":15,"area":"synth"},{"id":"2503.02877","title":"Weak-to-Strong Generalization Even in Random Feature Networks, Provably","created":"2025-03-04","cited_by_count":15,"area":null},{"id":"2411.00750","title":"Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling","created":"2024-11-01","cited_by_count":13,"area":"synth"},{"id":"2510.12225","title":"HoneyBee: Data Recipes for Vision-Language Reasoners","created":"2025-10-14","cited_by_count":13,"area":"lr"},{"id":"2410.18634","title":"Little Giants: Synthesizing High-Quality Embedding Data at Scale","created":"2024-10-24","cited_by_count":11,"area":null},{"id":"2502.03824","title":"Syntriever: How to Train Your Retriever with Synthetic Data from LLMs","created":"2025-02-06","cited_by_count":11,"area":"synth"},{"id":"2412.17061","title":"Multi-Agent Sampling: Scaling Inference Compute for Data Synthesis with Tree Search-Based Agentic Collaboration","created":"2024-12-22","cited_by_count":9,"area":"agents"},{"id":"2504.13101","title":"Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2412.12038","title":"LLMs for Cold-Start Cutting Plane Separator Configuration","created":"2024-12-16","cited_by_count":8,"area":null},{"id":"2505.18346","title":"On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective","created":"2025-05-23","cited_by_count":8,"area":null},{"id":"2604.07725","title":"Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution","created":"2026-04-09","cited_by_count":8,"area":null},{"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":"2502.17262","title":"Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective","created":"2025-02-24","cited_by_count":7,"area":null},{"id":"2503.04768","title":"DiMA: An LLM-Powered Ride-Hailing Assistant at DiDi","created":"2025-02-12","cited_by_count":7,"area":null},{"id":"2504.09802","title":"Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment","created":"2025-04-14","cited_by_count":7,"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":"2411.06839","title":"LLM-NEO: Parameter Efficient Knowledge Distillation for Large Language Models","created":"2024-11-11","cited_by_count":4,"area":"distill"},{"id":"2505.00031","title":"Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving","created":"2025-04-28","cited_by_count":4,"area":"synth"},{"id":"2505.21959","title":"EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2507.18584","title":"AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMs","created":"2025-07-24","cited_by_count":4,"area":"synth"},{"id":"2510.01111","title":"TsLLM: Augmenting LLMs for General Time Series Understanding and Prediction","created":"2025-10-01","cited_by_count":4,"area":null},{"id":"2410.17566","title":"Differentially Private Learning Needs Better Model Initialization and Self-Distillation","created":"2024-10-23","cited_by_count":3,"area":"distill"},{"id":"2509.17489","title":"MapCoder-Lite: Distilling Multi-Agent Coding into a Single Small LLM","created":"2025-09-22","cited_by_count":3,"area":"agents"},{"id":"2410.19456","title":"Computational Bottlenecks of Training Small-scale Large Language Models","created":"2024-10-25","cited_by_count":2,"area":null},{"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":"2505.21941","title":"Test-Time Scaling with Repeated Sampling Improves Multilingual Text Generation","created":"2025-05-28","cited_by_count":2,"area":"lr"},{"id":"2508.11975","title":"Chart-CoCa: Self-Improving Chart Understanding of Vision LMs via Code-Driven Synthesis and Candidate-Conditioned Answering","created":"2025-08-16","cited_by_count":2,"area":"mllm"},{"id":"2601.21522","title":"More Bang for the Buck: Improving the Inference of Large Language Models at a Fixed Budget using Reset and Discard (ReD)","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2605.05742","title":"Weak-to-Strong Generalization is Nearly Inevitable (in Linear Models)","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2607.12962","title":"Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models","created":"2026-07-14","cited_by_count":2,"area":null},{"id":"2410.04571","title":"EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles","created":"2024-10-06","cited_by_count":1,"area":null},{"id":"2410.08037","title":"Composite Learning Units: Generalized Learning Beyond Parameter Updates to Transform LLMs into Adaptive Reasoners","created":"2024-10-09","cited_by_count":1,"area":"lr"},{"id":"2412.15660","title":"Adaptable and Precise: Enterprise-Scenario LLM Function-Calling Capability Training Pipeline","created":"2024-12-20","cited_by_count":1,"area":"agents"},{"id":"2505.18011","title":"Training with Pseudo-Code for Instruction Following","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2506.19262","title":"What Matters in LLM-generated Data: Diversity and Its Effect on Model Fine-Tuning","created":"2025-06-24","cited_by_count":1,"area":"synth"},{"id":"2605.30789","title":"Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2507.00054","title":"Enhancing Reasoning Capabilities in SLMs with Reward Guided Dataset Distillation","created":"2025-06-25","cited_by_count":0,"area":"lr"},{"id":"2507.22250","title":"Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2605.09189","title":"Practical Scaling Laws: Converting Compute into Performance in a Data-Constrained World","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.17314","title":"Weak-to-Strong Elicitation via Mismatched Wrong Drafts","created":"2026-05-17","cited_by_count":0,"area":"lr"},{"id":"2607.01727","title":"When Does Generating More Help? Disentangling Fixed-Source Synthesis from Source Expansion in Synthetic Data Scaling","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.25826","title":"Unfolding Scientific Papers into Multi-Turn Generation Trajectories for Continued Pre-Training","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}