{"total":70,"rows":[{"id":"2501.09686","title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","created":"2025-01-16","cited_by_count":293,"area":"wm"},{"id":"2503.09572","title":"Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks","created":"2025-03-12","cited_by_count":195,"area":"agents"},{"id":"2406.09136","title":"Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs","created":"2024-06-13","cited_by_count":96,"area":"lr"},{"id":"2501.05707","title":"Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains","created":"2025-01-10","cited_by_count":95,"area":"lr"},{"id":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91,"area":null},{"id":"2502.02384","title":"STAIR: Improving Safety Alignment with Introspective Reasoning","created":"2025-02-04","cited_by_count":77,"area":"lr"},{"id":"2406.14491","title":"Instruction Pre-Training: Language Models are Supervised Multitask Learners","created":"2024-06-20","cited_by_count":63,"area":null},{"id":"2409.00608","title":"TinyAgent: Function Calling at the Edge","created":"2024-09-01","cited_by_count":58,"area":"agents"},{"id":"2502.04780","title":"SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning","created":"2025-02-07","cited_by_count":44,"area":"lr"},{"id":"2410.12896","title":"A Survey on Data Synthesis and Augmentation for Large Language Models","created":"2024-10-16","cited_by_count":41,"area":"synth"},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2408.08072","title":"I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm","created":"2024-08-15","cited_by_count":27,"area":null},{"id":"2409.02141","title":"Efficient and Scalable Estimation of Tool Representations in Vector Space","created":"2024-09-02","cited_by_count":22,"area":"agents"},{"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":"2412.07012","title":"ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models","created":"2024-12-09","cited_by_count":21,"area":"mllm"},{"id":"2503.17439","title":"LEMMA: Learning from Errors for MatheMatical Advancement in LLMs","created":"2025-03-21","cited_by_count":21,"area":"lr"},{"id":"2412.08467","title":"Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel","created":"2024-12-11","cited_by_count":20,"area":null},{"id":"2406.11736","title":"Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models","created":"2024-06-17","cited_by_count":14,"area":"synth"},{"id":"2407.04693","title":"ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models","created":"2024-07-05","cited_by_count":14,"area":null},{"id":"2408.05006","title":"COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis","created":"2024-08-09","cited_by_count":13,"area":"agents"},{"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":"2411.19930","title":"On Domain-Adaptive Post-Training for Multimodal Large Language Models","created":"2024-11-29","cited_by_count":13,"area":"mllm"},{"id":"2407.00497","title":"LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement","created":"2024-06-29","cited_by_count":11,"area":null},{"id":"2410.16930","title":"Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes","created":"2024-10-22","cited_by_count":10,"area":"lr"},{"id":"2503.23219","title":"Aurelia: Test-time Reasoning Distillation in Audio-Visual LLMs","created":"2025-03-29","cited_by_count":9,"area":"lr"},{"id":"2510.25817","title":"A Survey on Efficient Large Language Model Training: From Data-centric Perspectives","created":"2025-10-29","cited_by_count":9,"area":null},{"id":"2410.06491","title":"Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack","created":"2024-10-09","cited_by_count":8,"area":"alignment"},{"id":"2405.20830","title":"Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment","created":"2024-05-31","cited_by_count":7,"area":"alignment"},{"id":"2501.09368","title":"Aligning Instruction Tuning with Pre-training","created":"2025-01-16","cited_by_count":7,"area":null},{"id":"2508.21589","title":"Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning","created":"2025-08-29","cited_by_count":7,"area":null},{"id":"2410.02768","title":"Uncertainty-Guided Self-Questioning and Answering for Video-Language Alignment","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2411.00852","title":"EF-LLM: Energy Forecasting LLM with AI-assisted Automation, Enhanced Sparse Prediction, Hallucination Detection","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2412.15151","title":"Language Models as Continuous Self-Evolving Data Engineers","created":"2024-12-19","cited_by_count":6,"area":"synth"},{"id":"2507.00075","title":"Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier Gap","created":"2025-06-29","cited_by_count":6,"area":"synth"},{"id":"2512.00884","title":"Towards Active Synthetic Data Generation for Finetuning Language Models","created":"2025-11-30","cited_by_count":6,"area":"synth"},{"id":"2603.12658","title":"Beyond Static Models: An Evolving Framework for Continual Learning in Large Language Models across Training Stages","created":"2026-03-13","cited_by_count":6,"area":null},{"id":"2603.29791","title":"Reasoning-Driven Synthetic Data Generation and Evaluation","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2503.22006","title":"Enhancing Domain-Specific Encoder Models with LLM-Generated Data: How to Leverage Ontologies, and How to Do Without Them","created":"2025-03-27","cited_by_count":4,"area":"synth"},{"id":"2410.16534","title":"SoftSRV: Learn to Generate Targeted Synthetic Data","created":"2024-10-21","cited_by_count":3,"area":"synth"},{"id":"2502.17910","title":"Scaling LLM Pre-training with Vocabulary Curriculum","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2506.11040","title":"Large Language models for Time Series Analysis: Techniques, Applications, and Challenges","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2510.20449","title":"LM-mixup: Text Data Augmentation via Language Model based Mixup","created":"2025-10-23","cited_by_count":3,"area":"alignment"},{"id":"2408.16667","title":"Iterative Graph Alignment","created":"2024-08-29","cited_by_count":2,"area":null},{"id":"2412.15652","title":"Error-driven Data-efficient Large Multimodal Model Tuning","created":"2024-12-20","cited_by_count":2,"area":"mllm"},{"id":"2504.14523","title":"Learning from Reasoning Failures via Synthetic Data Generation","created":"2025-04-20","cited_by_count":2,"area":null},{"id":"2602.03414","title":"Socratic-Geo: Synthetic Data Generation and Geometric Reasoning via Multi-Agent Interaction","created":"2026-02-03","cited_by_count":2,"area":"lr"},{"id":"2406.08862","title":"Cognitively Inspired Energy-Based World Models","created":"2024-06-13","cited_by_count":1,"area":"wm"},{"id":"2406.11354","title":"Preserving Knowledge in Large Language Model with Model-Agnostic Self-Decompression","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2410.07880","title":"Unsupervised Data Validation Methods for Efficient Model Training","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2508.10315","title":"A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated Learning","created":"2025-08-14","cited_by_count":1,"area":"safety"},{"id":"2603.18009","title":"How Confident Is the First Token? An Uncertainty-Calibrated Prompt Optimization Framework for Large Language Model Classification and Understanding","created":"2026-02-23","cited_by_count":1,"area":"rag"},{"id":"2406.14867","title":"Investigating the Transferability of Code Repair for Low-Resource Programming Languages","created":"2024-06-21","cited_by_count":0,"area":null},{"id":"2408.04775","title":"Hybrid Student-Teacher Large Language Model Refinement for Cancer Toxicity Symptom Extraction","created":"2024-08-08","cited_by_count":0,"area":"rag"},{"id":"2410.02952","title":"Visual Editing with LLM-based Tool Chaining: An Efficient Distillation Approach for Real-Time Applications","created":"2024-10-03","cited_by_count":0,"area":null},{"id":"2501.07674","title":"CDS: Knowledge Component-Driven Data Synthesis Guided by Cognitive Diagnosis Theory","created":"2025-01-13","cited_by_count":0,"area":"synth"},{"id":"2502.05923","title":"ARISE: Iterative Rule Induction and Synthetic Data Generation for Text Classification","created":"2025-02-09","cited_by_count":0,"area":null},{"id":"2508.01869","title":"ProKG-Dial: Progressive Multi-Turn Dialogue Construction with Domain Knowledge Graphs","created":"2025-08-03","cited_by_count":0,"area":null},{"id":"2508.14723","title":"Transplant Then Regenerate: A New Paradigm for Text Data Augmentation","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2509.08022","title":"DiverValue-Bench: A Benchmark and Fine-Tuning Framework for Aligning Large Language Models with Diverse Human Values","created":"2025-09-09","cited_by_count":0,"area":"alignment"},{"id":"2602.19187","title":"Adaptive Problem Generation via Symbolic Representations","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2605.24296","title":"When Does Synthetic Patent Data Help? Volume-Fidelity Trade-offs in Low-Resource Multi-Label Classification","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2608.12340","title":"Class-Structure Preservation Beats Diversity: A Comprehensive Benchmark of Text Augmentation Methods for Imbalanced Text Classification","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2608.13545","title":"LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.22806","title":"DIAG: Diagnostic Iterative Alignment and Generation for Data-Efficient Mathematical Preference Distillation","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2608.23719","title":"ADE: Agentic Data Evolution Framework for Human-Centered Objectives","created":"2026-08-24","cited_by_count":0,"area":"agents"},{"id":"2609.29892","title":"Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.32431","title":"DualGuard: Dual-Mode Quality Control for Logic-Preserving Data Augmentation","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.34257","title":"Recursive LLM Degradation in Biomedical Question Answering: A Cross-Generation Study","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36750","title":"Group-Marginalized Self-Rewarding RL Drives Zero-Label Self-Evolving","created":"2026-09-29","cited_by_count":0,"area":"synth"},{"id":"2610.13285","title":"BoundaryEvo: Data-Model Co-Evolution at the Capability Boundary for Long-Chain Reasoning Distillation","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}