{"total":99,"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":"2408.15240","title":"Generative Verifiers: Reward Modeling as Next-Token Prediction","created":"2024-08-27","cited_by_count":480,"area":"lr"},{"id":"2410.08146","title":"Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning","created":"2024-10-10","cited_by_count":279,"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":"2410.01679","title":"VinePPO: Refining Credit Assignment in RL Training of LLMs","created":"2024-10-02","cited_by_count":183,"area":null},{"id":"2410.16198","title":"Improve Vision Language Model Chain-of-thought Reasoning","created":"2024-10-21","cited_by_count":136,"area":"lr"},{"id":"2502.06703","title":"Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling","created":"2025-02-10","cited_by_count":136,"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":"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":"2502.12118","title":"Scaling Test-Time Compute Without Verification or RL is Suboptimal","created":"2025-02-17","cited_by_count":84,"area":"lr"},{"id":"2410.11287","title":"Process Reward Model with Q-Value Rankings","created":"2024-10-15","cited_by_count":80,"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":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"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":"2509.07414","title":"Language Self-Play For Data-Free Training","created":"2025-09-09","cited_by_count":43,"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":"2502.12853","title":"S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning","created":"2025-02-18","cited_by_count":39,"area":"lr"},{"id":"2408.16333","title":"Self-Improving Diffusion Models with Synthetic Data","created":"2024-08-29","cited_by_count":35,"area":"diffusion"},{"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":"2502.06776","title":"InSTA: Towards Internet-Scale Training For Agents","created":"2025-02-10","cited_by_count":32,"area":"agents"},{"id":"2503.16212","title":"MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion","created":"2025-03-20","cited_by_count":30,"area":"lr"},{"id":"2410.08105","title":"What Makes Large Language Models Reason in (Multi-Turn) Code Generation?","created":"2024-10-10","cited_by_count":29,"area":"lr"},{"id":"2506.14674","title":"Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models","created":"2025-06-17","cited_by_count":28,"area":"wm"},{"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":"2408.13518","title":"Selective Preference Optimization via Token-Level Reward Function Estimation","created":"2024-08-24","cited_by_count":25,"area":"lr"},{"id":"2411.07681","title":"What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?","created":"2024-11-12","cited_by_count":23,"area":"lr"},{"id":"2409.06957","title":"Policy Filtration for RLHF to Mitigate Noise in Reward Models","created":"2024-09-11","cited_by_count":22,"area":"alignment"},{"id":"2410.16456","title":"To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning","created":"2024-10-21","cited_by_count":21,"area":null},{"id":"2411.00062","title":"Scalable Reinforcement Post-Training Beyond Static Human Prompts: Evolving Alignment via Asymmetric Self-Play","created":"2024-10-31","cited_by_count":21,"area":"alignment"},{"id":"2509.10127","title":"Population-Aligned Persona Generation for LLM-based Social Simulation","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2502.02584","title":"QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search","created":"2025-02-04","cited_by_count":20,"area":"lr"},{"id":"2505.11595","title":"Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO","created":"2025-05-16","cited_by_count":19,"area":"lr"},{"id":"2504.15362","title":"LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception","created":"2025-04-21","cited_by_count":16,"area":"lr"},{"id":"2601.18795","title":"Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes","created":"2026-01-26","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":"2410.01720","title":"Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective","created":"2024-10-02","cited_by_count":15,"area":"synth"},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2505.17063","title":"Synthetic Data RL: Task Definition Is All You Need","created":"2025-05-18","cited_by_count":15,"area":"lr"},{"id":"2506.15707","title":"Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling","created":"2025-05-30","cited_by_count":15,"area":"lr"},{"id":"2601.14209","title":"InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning","created":"2026-01-20","cited_by_count":14,"area":"lr"},{"id":"2605.11458","title":"Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning","created":"2026-05-12","cited_by_count":14,"area":"lr"},{"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":"2505.24273","title":"How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning","created":"2025-05-30","cited_by_count":13,"area":"lr"},{"id":"2507.02834","title":"ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning","created":"2025-07-03","cited_by_count":13,"area":"lr"},{"id":"2409.08642","title":"CPL: Critical Plan Step Learning Boosts LLM Generalization in Reasoning Tasks","created":"2024-09-13","cited_by_count":12,"area":"lr"},{"id":"2603.19880","title":"What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time","created":"2026-03-20","cited_by_count":12,"area":"lr"},{"id":"2509.25361","title":"Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling","created":"2025-09-29","cited_by_count":11,"area":"alignment"},{"id":"2410.13828","title":"A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement","created":"2024-10-17","cited_by_count":10,"area":"alignment"},{"id":"2512.23971","title":"CEC-Zero: Zero-Supervision Character Error Correction with Self-Generated Rewards","created":"2025-12-30","cited_by_count":10,"area":"synth"},{"id":"2408.13940","title":"Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning","created":"2024-08-25","cited_by_count":9,"area":"lr"},{"id":"2504.13145","title":"Exploring Expert Failures Improves LLM Agent Tuning","created":"2025-04-17","cited_by_count":9,"area":"agents"},{"id":"2504.18116","title":"Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models","created":"2025-04-25","cited_by_count":9,"area":"lr"},{"id":"2504.02327","title":"LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models","created":"2025-04-03","cited_by_count":8,"area":null},{"id":"2510.10815","title":"DRIFT: Decompose, Retrieve, Illustrate, then Formalize Theorems","created":"2025-10-12","cited_by_count":8,"area":null},{"id":"2511.03492","title":"Why Less is More (Sometimes): A Theory of Data Curation","created":"2025-11-05","cited_by_count":8,"area":null},{"id":"2511.09907","title":"Learning to Pose Problems: Reasoning-Driven and Solver-Adaptive Data Synthesis","created":"2025-11-13","cited_by_count":8,"area":"lr"},{"id":"2601.04809","title":"SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning","created":"2026-01-08","cited_by_count":8,"area":"lr"},{"id":"2505.07512","title":"ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution","created":"2025-05-12","cited_by_count":7,"area":"agents"},{"id":"2509.21623","title":"OjaKV: Context-Aware Online Low-Rank KV Cache Compression","created":"2025-09-25","cited_by_count":7,"area":"inference"},{"id":"2502.13723","title":"Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values","created":"2025-02-19","cited_by_count":6,"area":"lr"},{"id":"2505.16495","title":"ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation","created":"2025-05-22","cited_by_count":6,"area":"mllm"},{"id":"2603.12151","title":"IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL","created":"2026-03-12","cited_by_count":6,"area":null},{"id":"2504.14775","title":"gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling","created":"2025-04-21","cited_by_count":5,"area":"inference"},{"id":"2510.13501","title":"Confidence as a Reward: Transforming LLMs into Reward Models","created":"2025-10-15","cited_by_count":5,"area":"lr"},{"id":"2504.11364","title":"Offline Learning and Forgetting for Reasoning with Large Language Models","created":"2025-04-15","cited_by_count":4,"area":"lr"},{"id":"2510.08044","title":"Towards Reliable LLM-based Robot Planning via Combined Uncertainty Estimation","created":"2025-10-09","cited_by_count":4,"area":"lr"},{"id":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"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":"2512.14220","title":"Estimating problem difficulty without ground truth using Large Language Model comparisons","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2604.09107","title":"TensorHub: Scalable and Elastic Weight Transfer for LLM RL Training","created":"2026-04-10","cited_by_count":4,"area":null},{"id":"2504.19024","title":"KETCHUP: K-Step Return Estimation for Sequential Knowledge Distillation","created":"2025-04-26","cited_by_count":3,"area":"distill"},{"id":"2510.17923","title":"Rewarding the Journey, Not Just the Destination: A Composite Path and Answer Self-Scoring Reward Mechanism for Test-Time Reinforcement Learning","created":"2025-10-20","cited_by_count":3,"area":"alignment"},{"id":"2501.18962","title":"Spend Wisely: Maximizing Post-Training Gains in Iterative Synthetic Data Bootstrapping","created":"2025-01-31","cited_by_count":2,"area":"synth"},{"id":"2505.12500","title":"MARGE: Improving Math Reasoning for LLMs with Guided Exploration","created":"2025-05-18","cited_by_count":2,"area":"lr"},{"id":"2506.00741","title":"Data Swarms: Optimizable Generation of Synthetic Evaluation Data","created":"2025-05-31","cited_by_count":2,"area":null},{"id":"2506.17533","title":"DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning","created":"2025-06-21","cited_by_count":2,"area":"lr"},{"id":"2511.03928","title":"SynQuE: Estimating Synthetic Dataset Quality Without Annotations","created":"2025-11-06","cited_by_count":2,"area":"synth"},{"id":"2511.05705","title":"Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale","created":"2025-11-07","cited_by_count":2,"area":"lr"},{"id":"2602.11351","title":"Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization","created":"2026-02-11","cited_by_count":2,"area":"agents"},{"id":"2604.19060","title":"Reinforcement Learning Improves LLM Accuracy and Reasoning in Disease Classification from Radiology Reports","created":"2026-04-21","cited_by_count":2,"area":"lr"},{"id":"2411.05209","title":"Alopex: A Computational Framework for Enabling On-Device Function Calls with LLMs","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2509.19893","title":"Future Policy Approximation for Offline Reinforcement Learning in LLM Reasoning","created":"2025-09-24","cited_by_count":1,"area":"lr"},{"id":"2602.15327","title":"Prescriptive Scaling Reveals the Evolution of Language Model Capabilities","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2604.03472","title":"Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.04894","title":"Asymmetric Advantage Modulation Calibrates Entropy Dynamics in RLVR","created":"2026-04-06","cited_by_count":1,"area":"lr"},{"id":"2605.08472","title":"Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models","created":"2026-05-08","cited_by_count":1,"area":"synth"},{"id":"2605.20873","title":"PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2608.03545","title":"Hi-TTRL: Regulating Consensus with Hints for Test-Time Reinforcement Learning","created":"2026-08-04","cited_by_count":1,"area":"lr"},{"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":"2507.21584","title":"TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs","created":"2025-07-29","cited_by_count":0,"area":"mllm"},{"id":"2510.08572","title":"BLAZER: Bootstrapping LLM-based Manipulation Agents with Zero-Shot Data Generation","created":"2025-10-09","cited_by_count":0,"area":"agents"},{"id":"2602.18437","title":"FineRef: Fine-Grained Error Reflection and Correction for Long-Form Generation with Citations","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2602.19187","title":"Adaptive Problem Generation via Symbolic Representations","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2605.20256","title":"FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning","created":"2026-05-18","cited_by_count":0,"area":"lr"},{"id":"2606.11470","title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2609.12353","title":"SynthSentry: Detecting Synthetic Data Contamination in Language Model Training Data","created":"2026-09-11","cited_by_count":0,"area":"synth"},{"id":"2609.25442","title":"WeightBridge: An Efficient Weight Transfer Library for Reinforcement Learning","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.30391","title":"From Weak Data to Strong Policy: Q-Targets Enable Provable In-Context Reinforcement Learning","created":"2026-09-24","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}