{"total":59,"rows":[{"id":"2511.10395","title":"AgentEvolver: Towards Efficient Self-Evolving Agent System","created":"2025-11-13","cited_by_count":85,"area":"agents"},{"id":"2502.12118","title":"Scaling Test-Time Compute Without Verification or RL is Suboptimal","created":"2025-02-17","cited_by_count":84,"area":"lr"},{"id":"2504.12522","title":"Evaluating the Diversity and Quality of LLM Generated Content","created":"2025-04-16","cited_by_count":51,"area":"lr"},{"id":"2502.12671","title":"Baichuan-M1: Pushing the Medical Capability of Large Language Models","created":"2025-02-18","cited_by_count":43,"area":null},{"id":"2505.20161","title":"Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning","created":"2025-05-26","cited_by_count":40,"area":"lr"},{"id":"2412.02980","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","created":"2024-12-04","cited_by_count":35,"area":"synth"},{"id":"2510.01631","title":"Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls","created":"2025-10-02","cited_by_count":26,"area":"synth"},{"id":"2505.02881","title":"Rewriting Pre-Training Data Boosts LLM Performance in Math and Code","created":"2025-05-05","cited_by_count":21,"area":"lr"},{"id":"2502.19402","title":"General Intelligence Requires Reward-based Pretraining","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2502.01697","title":"BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation","created":"2025-02-03","cited_by_count":8,"area":"synth"},{"id":"2510.06499","title":"Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels","created":"2025-10-07","cited_by_count":8,"area":"offlinerl"},{"id":"2511.13945","title":"Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers","created":"2025-11-17","cited_by_count":8,"area":null},{"id":"2601.11895","title":"DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models","created":"2026-01-17","cited_by_count":8,"area":null},{"id":"2511.15593","title":"What Does It Take to Be a Good AI Research Agent? Studying the Role of Ideation Diversity","created":"2025-11-19","cited_by_count":7,"area":"agents"},{"id":"2510.10681","title":"RePro: Training Language Models to Faithfully Recycle the Web for Pretraining","created":"2025-10-12","cited_by_count":6,"area":null},{"id":"2510.16657","title":"Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence","created":"2025-10-18","cited_by_count":6,"area":"synth"},{"id":"2601.17717","title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","created":"2026-01-25","cited_by_count":6,"area":"synth"},{"id":"2508.06595","title":"LLM Unlearning Without an Expert Curated Dataset","created":"2025-08-08","cited_by_count":5,"area":"safety"},{"id":"2601.09066","title":"Mi:dm 2.0 Korea-centric Bilingual Language Models","created":"2026-01-14","cited_by_count":5,"area":null},{"id":"2603.25681","title":"Self-Improvement of Large Language Models: A Technical Overview and Future Outlook","created":"2026-03-26","cited_by_count":5,"area":"synth"},{"id":"2603.29791","title":"Reasoning-Driven Synthetic Data Generation and Evaluation","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2502.03323","title":"Out-of-Distribution Detection using Synthetic Data Generation","created":"2025-02-05","cited_by_count":4,"area":"synth"},{"id":"2505.18458","title":"A Survey of LLM $\\times$ DATA","created":"2025-05-24","cited_by_count":4,"area":"rag"},{"id":"2510.09426","title":"KORMo: Korean Open Reasoning Model for Everyone","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2603.06603","title":"Scale Dependent Data Duplication","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2505.24768","title":"From Macro to Micro: Probing Dataset Diversity in Language Model Fine-Tuning","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2507.17578","title":"Synthetic Voice Data for Automatic Speech Recognition in African Languages","created":"2025-07-23","cited_by_count":3,"area":null},{"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":"2601.09966","title":"A Sustainable AI Economy Needs Data Deals That Work for Generators","created":"2026-01-15","cited_by_count":3,"area":null},{"id":"2602.12172","title":"Pedagogically-Inspired Data Synthesis for Language Model Knowledge Distillation","created":"2026-02-12","cited_by_count":3,"area":"synth"},{"id":"2508.04337","title":"Modelling and Classifying the Components of a Literature Review","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2509.22480","title":"Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2605.17849","title":"Generating Pretraining Tokens from Organic Data for Data-Bound Scaling","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2608.24065","title":"Mechanistic Circuit Identification for Controllable Data Generation","created":"2026-08-25","cited_by_count":2,"area":null},{"id":"2410.18529","title":"Instructional Text Across Disciplines: A Survey of Representations, Downstream Tasks, and Open Challenges Toward Capable AI Agents","created":"2024-10-24","cited_by_count":1,"area":"agents"},{"id":"2503.07660","title":"Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization","created":"2025-03-08","cited_by_count":1,"area":"alignment"},{"id":"2505.19848","title":"Improving Multilingual Math Reasoning for African Languages","created":"2025-05-26","cited_by_count":1,"area":"lr"},{"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":"2507.18055","title":"Privacy-Preserving Synthetic Review Generation with Diverse Writing Styles Using LLMs","created":"2025-07-24","cited_by_count":1,"area":"synth"},{"id":"2509.20837","title":"Verification Limits Code LLM Training","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2509.25148","title":"AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models","created":"2025-09-29","cited_by_count":1,"area":"alignment"},{"id":"2511.13640","title":"Data Value in the Age of Scaling: Understanding LLM Scaling Dynamics Under Real-Synthetic Data Mixtures","created":"2025-11-17","cited_by_count":1,"area":"synth"},{"id":"2602.04785","title":"Team, Then Trim: An Assembly-Line LLM Framework for High-Quality Tabular Data Generation","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.11217","title":"The Magic Correlations: Understanding Knowledge Transfer from Pretraining to Supervised Fine-Tuning","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.18361","title":"Synthetic Data Generation for Training Diversified Commonsense Reasoning Models","created":"2026-03-18","cited_by_count":1,"area":"lr"},{"id":"2411.16730","title":"\"Moralized\" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks","created":"2024-11-23","cited_by_count":0,"area":"safety"},{"id":"2506.03051","title":"Facts Do Care About Your Language: Assessing Answer Quality of Multilingual LLMs","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2506.19089","title":"Language Models Might Not Understand You: Evaluating Theory of Mind via Story Prompting","created":"2025-06-23","cited_by_count":0,"area":"wm"},{"id":"2510.11842","title":"Balancing Synthetic Data and Replay for Enhancing Task-Specific Capabilities","created":"2025-10-13","cited_by_count":0,"area":"synth"},{"id":"2511.09488","title":"AutoSynth: Automated Workflow Optimization for High-Quality Synthetic Dataset Generation via Monte Carlo Tree Search","created":"2025-11-12","cited_by_count":0,"area":"synth"},{"id":"2511.12782","title":"LLM Reinforcement in Context","created":"2025-11-16","cited_by_count":0,"area":"alignment"},{"id":"2512.03001","title":"Invasive Context Engineering to Control Large Language Models","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2602.08237","title":"Document Reconstruction Unlocks Scalable Long-Context RLVR","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2604.26170","title":"EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2609.00184","title":"Synthetic Worlds for Temporal Evaluation and Knowledge Updating in LLMs","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.09572","title":"Learning with Synthetic Data via SGD in High-Dimensional Linear Regression","created":"2026-09-09","cited_by_count":0,"area":"synth"},{"id":"2609.33666","title":"One Model Is Not a Crowd: Multi-LLM and Aspect-Conditioned Diverse Comment Generation","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.00779","title":"Effective Synthetic Data Curation Requires Group-Level Signals","created":"2026-09-30","cited_by_count":0,"area":"synth"},{"id":"2610.12829","title":"Scalable Learning of Determinantal Point Processes with Kernel-Structured Interactions","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}