{"total":349,"rows":[{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986,"area":"lr"},{"id":"2409.12122","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","created":"2024-09-18","cited_by_count":1090,"area":"synth"},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557,"area":"synth"},{"id":"2503.18892","title":"SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild","created":"2025-03-24","cited_by_count":511,"area":"lr"},{"id":"2408.15240","title":"Generative Verifiers: Reward Modeling as Next-Token Prediction","created":"2024-08-27","cited_by_count":480,"area":"lr"},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"id":"2409.12917","title":"Training Language Models to Self-Correct via Reinforcement Learning","created":"2024-09-19","cited_by_count":426,"area":"lr"},{"id":"2505.22954","title":"Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents","created":"2025-05-29","cited_by_count":356,"area":"agents"},{"id":"2406.03816","title":"ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search","created":"2024-06-06","cited_by_count":344,"area":"lr"},{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328,"area":null},{"id":"2502.03373","title":"Demystifying Long Chain-of-Thought Reasoning in LLMs","created":"2025-02-05","cited_by_count":326,"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":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2410.08146","title":"Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning","created":"2024-10-10","cited_by_count":279,"area":"lr"},{"id":"2404.19733","title":"Iterative Reasoning Preference Optimization","created":"2024-04-30","cited_by_count":246,"area":"lr"},{"id":"2401.08967","title":"ReFT: Reasoning with Reinforced Fine-Tuning","created":"2024-01-17","cited_by_count":239,"area":"lr"},{"id":"2405.00675","title":"Self-Play Preference Optimization for Language Model Alignment","created":"2024-05-01","cited_by_count":232,"area":"alignment"},{"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":"2402.06457","title":"V-STaR: Training Verifiers for Self-Taught Reasoners","created":"2024-02-09","cited_by_count":217,"area":"lr"},{"id":"2408.07199","title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents","created":"2024-08-13","cited_by_count":208,"area":"lr"},{"id":"2404.11018","title":"Many-Shot In-Context Learning","created":"2024-04-17","cited_by_count":206,"area":null},{"id":"2504.07079","title":"SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills","created":"2025-04-09","cited_by_count":192,"area":"agents"},{"id":"2410.01679","title":"VinePPO: Refining Credit Assignment in RL Training of LLMs","created":"2024-10-02","cited_by_count":183,"area":null},{"id":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178,"area":"alignment"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2503.17352","title":"OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles","created":"2025-03-21","cited_by_count":124,"area":"lr"},{"id":"2503.07572","title":"Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning","created":"2025-03-10","cited_by_count":123,"area":"lr"},{"id":"2406.04151","title":"AgentGym: Evolving Large Language Model-based Agents across Diverse Environments","created":"2024-06-06","cited_by_count":120,"area":"agents"},{"id":"2402.06332","title":"InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning","created":"2024-02-09","cited_by_count":119,"area":"lr"},{"id":"2504.16828","title":"Process Reward Models That Think","created":"2025-04-23","cited_by_count":118,"area":"lr"},{"id":"2406.15951","title":"Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration","created":"2024-06-22","cited_by_count":113,"area":"alignment"},{"id":"2502.12143","title":"Small Models Struggle to Learn from Strong Reasoners","created":"2025-02-17","cited_by_count":113,"area":"lr"},{"id":"2405.08448","title":"Understanding the performance gap between online and offline alignment algorithms","created":"2024-05-14","cited_by_count":110,"area":"alignment"},{"id":"2501.04682","title":"Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought","created":"2025-01-08","cited_by_count":109,"area":"lr"},{"id":"2402.18563","title":"Approaching Human-Level Forecasting with Language Models","created":"2024-02-28","cited_by_count":107,"area":null},{"id":"2505.22660","title":"Maximizing Confidence Alone Improves Reasoning","created":"2025-05-28","cited_by_count":100,"area":"lr"},{"id":"2406.14532","title":"RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold","created":"2024-06-20","cited_by_count":99,"area":"lr"},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"area":"alignment"},{"id":"2405.20304","title":"Group Robust Preference Optimization in Reward-free RLHF","created":"2024-05-30","cited_by_count":95,"area":"lr"},{"id":"2407.13690","title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","created":"2024-06-18","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":"2412.15287","title":"Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models","created":"2024-12-18","cited_by_count":89,"area":"lr"},{"id":"2406.11176","title":"Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement","created":"2024-06-17","cited_by_count":88,"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":"2502.13124","title":"NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions","created":"2025-02-18","cited_by_count":84,"area":"lr"},{"id":"2506.10943","title":"Self-Adapting Language Models","created":"2025-06-12","cited_by_count":84,"area":null},{"id":"2404.10642","title":"Self-playing Adversarial Language Game Enhances LLM Reasoning","created":"2024-04-16","cited_by_count":83,"area":"lr"},{"id":"2402.19450","title":"Functional Benchmarks for Robust Evaluation of Reasoning Performance, and the Reasoning Gap","created":"2024-02-29","cited_by_count":79,"area":"lr"},{"id":"2412.01928","title":"MALT: Improving Reasoning with Multi-Agent LLM Training","created":"2024-12-02","cited_by_count":76,"area":"lr"},{"id":"2505.23564","title":"Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models","created":"2025-05-29","cited_by_count":75,"area":"lr"},{"id":"2402.16352","title":"MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs","created":"2024-02-26","cited_by_count":72,"area":"lr"},{"id":"2403.15042","title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","created":"2024-03-22","cited_by_count":70,"area":null},{"id":"2410.18252","title":"Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models","created":"2024-10-23","cited_by_count":70,"area":"alignment"},{"id":"2502.19613","title":"Self-rewarding correction for mathematical reasoning","created":"2025-02-26","cited_by_count":70,"area":"lr"},{"id":"2407.10040","title":"Lean-STaR: Learning to Interleave Thinking and Proving","created":"2024-07-14","cited_by_count":68,"area":"lr"},{"id":"2604.12002","title":"Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision","created":"2026-04-13","cited_by_count":68,"area":"distill"},{"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":"2503.14286","title":"Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMs","created":"2025-03-18","cited_by_count":61,"area":null},{"id":"2501.11284","title":"RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?","created":"2025-01-20","cited_by_count":60,"area":"lr"},{"id":"2405.20309","title":"Large Language Models Can Self-Improve At Web Agent Tasks","created":"2024-05-30","cited_by_count":55,"area":"agents"},{"id":"2412.16145","title":"Offline Reinforcement Learning for LLM Multi-Step Reasoning","created":"2024-12-20","cited_by_count":54,"area":"lr"},{"id":"2506.04210","title":"Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models","created":"2025-06-04","cited_by_count":53,"area":"lr"},{"id":"2501.18101","title":"Diverse Preference Optimization","created":"2025-01-30","cited_by_count":52,"area":"lr"},{"id":"2502.06781","title":"Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning","created":"2025-02-10","cited_by_count":52,"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":"2411.04109","title":"Self-Consistency Preference Optimization","created":"2024-11-06","cited_by_count":50,"area":"lr"},{"id":"2502.01839","title":"Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification","created":"2025-02-03","cited_by_count":50,"area":"lr"},{"id":"2508.03682","title":"Self-Questioning Language Models","created":"2025-08-05","cited_by_count":50,"area":null},{"id":"2402.00658","title":"Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing","created":"2024-02-01","cited_by_count":49,"area":"lr"},{"id":"2505.23614","title":"Inference-time Scaling of Diffusion Models through Classical Search","created":"2025-05-29","cited_by_count":49,"area":"lr"},{"id":"2411.02306","title":"On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback","created":"2024-11-04","cited_by_count":47,"area":"alignment"},{"id":"2503.18866","title":"Reasoning to Learn from Latent Thoughts","created":"2025-03-24","cited_by_count":45,"area":"lr"},{"id":"2504.04736","title":"Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use","created":"2025-04-07","cited_by_count":45,"area":"lr"},{"id":"2410.08115","title":"Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System","created":"2024-10-10","cited_by_count":43,"area":"agents"},{"id":"2409.12993","title":"CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair","created":"2024-09-19","cited_by_count":42,"area":"synth"},{"id":"2412.08442","title":"From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons","created":"2024-12-11","cited_by_count":42,"area":"mllm"},{"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":"2505.19683","title":"Large Language Models for Planning: A Comprehensive and Systematic Survey","created":"2025-05-26","cited_by_count":40,"area":"lr"},{"id":"2604.01193","title":"Embarrassingly Simple Self-Distillation Improves Code Generation","created":"2026-04-01","cited_by_count":40,"area":"distill"},{"id":"2507.12856","title":"Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)","created":"2025-07-17","cited_by_count":38,"area":"lr"},{"id":"2503.12854","title":"Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation","created":"2025-03-17","cited_by_count":37,"area":"lr"},{"id":"2602.04837","title":"Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharing","created":"2026-02-04","cited_by_count":36,"area":"synth"},{"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":"2602.20574","title":"GATES: Self-Distillation under Privileged Context with Consensus Gating","created":"2026-02-24","cited_by_count":35,"area":"distill"},{"id":"2607.07663","title":"Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops","created":"2026-07-08","cited_by_count":35,"area":null},{"id":"2403.08140","title":"BAGEL: Bootstrapping Agents by Guiding Exploration with Language","created":"2024-03-12","cited_by_count":34,"area":"agents"},{"id":"2407.13647","title":"Weak-to-Strong Reasoning","created":"2024-07-18","cited_by_count":33,"area":"lr"},{"id":"2405.17888","title":"Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment","created":"2024-05-28","cited_by_count":32,"area":"alignment"},{"id":"2412.17451","title":"Diving into Self-Evolving Training for Multimodal Reasoning","created":"2024-12-23","cited_by_count":32,"area":"lr"},{"id":"2501.07861","title":"ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding","created":"2025-01-14","cited_by_count":32,"area":"lr"},{"id":"2507.23751","title":"CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks","created":"2025-07-31","cited_by_count":32,"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":"2503.02875","title":"The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models","created":"2025-03-04","cited_by_count":31,"area":"lr"},{"id":"2406.05673","title":"Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples","created":"2024-06-09","cited_by_count":30,"area":"lr"},{"id":"2410.01748","title":"Not All LLM Reasoners Are Created Equal","created":"2024-10-02","cited_by_count":30,"area":"lr"},{"id":"2503.19618","title":"Beyond Verifiable Rewards: Scaling Reinforcement Learning for Language Models to Unverifiable Data","created":"2025-03-25","cited_by_count":29,"area":null},{"id":"2412.08819","title":"HARP: A challenging human-annotated math reasoning benchmark","created":"2024-12-11","cited_by_count":27,"area":"lr"},{"id":"2509.18314","title":"Exploiting Tree Structure for Credit Assignment in RL Training of LLMs","created":"2025-09-22","cited_by_count":27,"area":"lr"},{"id":"2407.18248","title":"Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning","created":"2024-07-25","cited_by_count":26,"area":"lr"}],"next_cursor":"100"}