{"total":121,"rows":[{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112,"area":null},{"id":"2412.01951","title":"Self-Improvement in Language Models: The Sharpening Mechanism","created":"2024-12-02","cited_by_count":104,"area":"synth"},{"id":"2503.21878","title":"Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment","created":"2025-03-27","cited_by_count":97,"area":"alignment"},{"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":"2407.14622","title":"BOND: Aligning LLMs with Best-of-N Distillation","created":"2024-07-19","cited_by_count":76,"area":"alignment"},{"id":"2409.13156","title":"RRM: Robust Reward Model Training Mitigates Reward Hacking","created":"2024-09-20","cited_by_count":76,"area":"alignment"},{"id":"2502.12215","title":"Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?","created":"2025-02-17","cited_by_count":70,"area":"lr"},{"id":"2410.08847","title":"Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization","created":"2024-10-11","cited_by_count":67,"area":"alignment"},{"id":"2506.22716","title":"BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute","created":"2025-06-28","cited_by_count":67,"area":null},{"id":"2409.02392","title":"Building Math Agents with Multi-Turn Iterative Preference Learning","created":"2024-09-04","cited_by_count":66,"area":"lr"},{"id":"2509.21100","title":"VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception","created":"2025-09-25","cited_by_count":65,"area":"lr"},{"id":"2503.01422","title":"Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding","created":"2025-03-03","cited_by_count":63,"area":"lr"},{"id":"2410.09893","title":"RMB: Comprehensively Benchmarking Reward Models in LLM Alignment","created":"2024-10-13","cited_by_count":61,"area":"alignment"},{"id":"2410.16033","title":"TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling","created":"2024-10-18","cited_by_count":61,"area":"lr"},{"id":"2502.00674","title":"Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?","created":"2025-02-02","cited_by_count":54,"area":"lr"},{"id":"2509.21500","title":"Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training","created":"2025-09-25","cited_by_count":53,"area":"alignment"},{"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":"2407.06057","title":"Variational Best-of-N Alignment","created":"2024-07-08","cited_by_count":51,"area":"alignment"},{"id":"2412.14135","title":"Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective","created":"2024-12-18","cited_by_count":50,"area":"lr"},{"id":"2507.12508","title":"MindJourney: Test-Time Scaling with World Models for Spatial Reasoning","created":"2025-07-16","cited_by_count":50,"area":"wm"},{"id":"2409.11704","title":"From Lists to Emojis: How Format Bias Affects Model Alignment","created":"2024-09-18","cited_by_count":49,"area":"alignment"},{"id":"2504.13139","title":"Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo","created":"2025-04-17","cited_by_count":46,"area":null},{"id":"2505.20674","title":"PonderLM: Pretraining Language Models to Ponder in Continuous Space","created":"2025-05-27","cited_by_count":44,"area":null},{"id":"2501.02497","title":"A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning","created":"2025-01-05","cited_by_count":40,"area":"lr"},{"id":"2502.12668","title":"Evaluation of Best-of-N Sampling Strategies for Language Model Alignment","created":"2025-02-18","cited_by_count":39,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2412.19792","title":"InfAlign: Inference-aware language model alignment","created":"2024-12-27","cited_by_count":35,"area":"alignment"},{"id":"2506.19248","title":"Inference-Time Reward Hacking in Large Language Models","created":"2025-06-24","cited_by_count":34,"area":"alignment"},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"id":"2505.03156","title":"Soft Best-of-n Sampling for Model Alignment","created":"2025-05-06","cited_by_count":30,"area":"alignment"},{"id":"2502.11517","title":"Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding","created":"2025-02-17","cited_by_count":28,"area":"inference"},{"id":"2410.05495","title":"Self-rationalization improves LLM as a fine-grained judge","created":"2024-10-07","cited_by_count":27,"area":null},{"id":"2505.22866","title":"Scaling Offline RL via Efficient and Expressive Shortcut Models","created":"2025-05-28","cited_by_count":27,"area":"offlinerl"},{"id":"2503.22230","title":"Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback","created":"2025-03-28","cited_by_count":26,"area":"alignment"},{"id":"2605.12474","title":"Reward Hacking in Rubric-Based Reinforcement Learning","created":"2026-05-12","cited_by_count":26,"area":"alignment"},{"id":"2406.07327","title":"3D-Properties: Identifying Challenges in DPO and Charting a Path Forward","created":"2024-06-11","cited_by_count":24,"area":"alignment"},{"id":"2602.01002","title":"How RLHF Amplifies Sycophancy","created":"2026-02-01","cited_by_count":23,"area":"alignment"},{"id":"2502.07460","title":"Logarithmic Regret for Online KL-Regularized Reinforcement Learning","created":"2025-02-11","cited_by_count":22,"area":"alignment"},{"id":"2504.03790","title":"Sample, Don't Search: Rethinking Test-Time Alignment for Language Models","created":"2025-04-04","cited_by_count":22,"area":"lr"},{"id":"2409.16636","title":"Training Language Models to Win Debates with Self-Play Improves Judge Accuracy","created":"2024-09-25","cited_by_count":16,"area":"synth"},{"id":"2505.07787","title":"Learning from Peers in Reasoning Models","created":"2025-05-12","cited_by_count":16,"area":"lr"},{"id":"2508.00890","title":"AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks","created":"2025-07-26","cited_by_count":16,"area":"lr"},{"id":"2509.23184","title":"PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space","created":"2025-09-27","cited_by_count":16,"area":"lr"},{"id":"2510.23393","title":"The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation","created":"2025-10-27","cited_by_count":16,"area":null},{"id":"2506.01320","title":"Psi-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models","created":"2025-06-02","cited_by_count":15,"area":"diffusion"},{"id":"2511.01008","title":"MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL","created":"2025-11-02","cited_by_count":15,"area":"agents"},{"id":"2604.16004","title":"AgentV-RL: Scaling Reward Modeling with Agentic Verifier","created":"2026-04-17","cited_by_count":15,"area":"lr"},{"id":"2502.00968","title":"CoDe: Blockwise Control for Denoising Diffusion Models","created":"2025-02-03","cited_by_count":14,"area":"diffusion"},{"id":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"id":"2509.24261","title":"Risk-Sensitive RL for Alleviating Exploration Dilemmas in Large Language Models","created":"2025-09-29","cited_by_count":14,"area":"lr"},{"id":"2506.12109","title":"Personalized LLM Decoding via Contrasting Personal Preference","created":"2025-06-13","cited_by_count":12,"area":"alignment"},{"id":"2507.12399","title":"ROC-n-reroll: How verifier imperfection affects test-time scaling","created":"2025-07-16","cited_by_count":12,"area":"lr"},{"id":"2508.02511","title":"Test-time Prompt Intervention","created":"2025-08-04","cited_by_count":12,"area":"lr"},{"id":"2510.17472","title":"Certified Self-Consistency: Statistical Guarantees and Test-Time Training for Reliable Reasoning in LLMs","created":"2025-10-20","cited_by_count":12,"area":"lr"},{"id":"2507.07375","title":"Bradley-Terry and Multi-Objective Reward Modeling Are Complementary","created":"2025-07-10","cited_by_count":11,"area":"alignment"},{"id":"2410.20727","title":"Faster WIND: Accelerating Iterative Best-of-$N$ Distillation for LLM Alignment","created":"2024-10-28","cited_by_count":9,"area":"alignment"},{"id":"2505.12050","title":"AdaBoN: Adaptive Best-of-N Alignment","created":"2025-05-17","cited_by_count":9,"area":"alignment"},{"id":"2509.24771","title":"LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space","created":"2025-09-29","cited_by_count":9,"area":"lr"},{"id":"2502.04354","title":"Reviving The Classics: Active Reward Modeling in Large Language Model Alignment","created":"2025-02-04","cited_by_count":8,"area":"alignment"},{"id":"2605.22817","title":"Vector Policy Optimization: Training for Diversity Improves Test-Time Search","created":"2026-05-21","cited_by_count":8,"area":null},{"id":"2406.01423","title":"Value Improved Actor Critic Algorithms","created":"2024-06-03","cited_by_count":7,"area":"deeprl"},{"id":"2505.12843","title":"Bias Fitting to Mitigate Length Bias of Reward Model in RLHF","created":"2025-05-19","cited_by_count":7,"area":"alignment"},{"id":"2505.18547","title":"Diffusion Blend: Inference-Time Multi-Preference Alignment for Diffusion Models","created":"2025-05-24","cited_by_count":7,"area":"diffusion"},{"id":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2602.11767","title":"TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents","created":"2026-02-12","cited_by_count":7,"area":"agents"},{"id":"2505.18601","title":"Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators","created":"2025-05-24","cited_by_count":6,"area":"lr"},{"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":"2510.08218","title":"Expressive Value Learning for Scalable Offline Reinforcement Learning","created":"2025-10-09","cited_by_count":6,"area":"diffusion"},{"id":"2512.02874","title":"Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning","created":"2025-12-02","cited_by_count":6,"area":"lr"},{"id":"2505.00147","title":"AdaptMI: Adaptive Skill-based In-context Math Instruction for Small Language Models","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2508.01174","title":"RSPO: Risk-Seeking Policy Optimization for Pass@k and Max@k Metrics in Large Language Models","created":"2025-08-02","cited_by_count":5,"area":null},{"id":"2510.03777","title":"GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time","created":"2025-10-04","cited_by_count":5,"area":null},{"id":"2603.14128","title":"Diffusion Reinforcement Learning via Centered Reward Distillation","created":"2026-03-14","cited_by_count":5,"area":"diffusion"},{"id":"2605.04542","title":"Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation","created":"2026-05-06","cited_by_count":5,"area":"lr"},{"id":"2506.17251","title":"Training-free LLM Verification via Recycling Few-shot Examples","created":"2025-06-08","cited_by_count":4,"area":"lr"},{"id":"2510.02692","title":"Fine-Tuning Diffusion Models via Intermediate Distribution Shaping","created":"2025-10-03","cited_by_count":4,"area":"diffusion"},{"id":"2512.00706","title":"Optimizing LVLMs with On-Policy Data for Effective Hallucination Mitigation","created":"2025-11-30","cited_by_count":4,"area":"mllm"},{"id":"2604.02507","title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","created":"2026-04-02","cited_by_count":4,"area":"alignment"},{"id":"2501.15631","title":"BoKDiff: Best-of-K Diffusion Alignment for Target-Specific 3D Molecule Generation","created":"2025-01-26","cited_by_count":3,"area":null},{"id":"2502.10505","title":"Preference learning made easy: Everything should be understood through win rate","created":"2025-02-14","cited_by_count":3,"area":null},{"id":"2508.03333","title":"CTTS: Collective Test-Time Scaling","created":"2025-08-05","cited_by_count":3,"area":"lr"},{"id":"2512.07898","title":"MARINE: Theoretical Optimization and Design for Multi-Agent Recursive IN-context Enhancement","created":"2025-12-05","cited_by_count":3,"area":"lr"},{"id":"2603.06797","title":"Best-of-Tails: Bridging Optimism and Pessimism in Inference-Time Alignment","created":"2026-03-06","cited_by_count":3,"area":"alignment"},{"id":"2510.21667","title":"FlowSynth: Instrument Generation Through Distributional Flow Matching and Test-Time Search","created":"2025-10-24","cited_by_count":2,"area":"diffusion"},{"id":"2510.27206","title":"Fints: Efficient Inference-Time Personalization for LLMs with Fine-Grained Instance-Tailored Steering","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2512.13262","title":"Post-Training and Test-Time Scaling of Generative Agent Behavior Models for Interactive Autonomous Driving","created":"2025-12-15","cited_by_count":2,"area":"lr"},{"id":"2601.08343","title":"When KV Cache Reuse Fails in Multi-Agent Systems: Cross-Candidate Interaction is Crucial for LLM Judges","created":"2026-01-13","cited_by_count":2,"area":"agents"},{"id":"2602.03787","title":"Inference-time Unlearning Using Conformal Prediction","created":"2026-02-03","cited_by_count":2,"area":"safety"},{"id":"2604.04379","title":"Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning","created":"2026-04-06","cited_by_count":2,"area":"mllm"},{"id":"2604.12196","title":"Beyond Majority Voting: Efficient Best-Of-N with Radial Consensus Score","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2606.03962","title":"Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning","created":"2026-06-02","cited_by_count":2,"area":"alignment"},{"id":"2607.04728","title":"Turning Off-Policy Tokens On-Policy: A Plug-in Approach for Improving LLM Alignment","created":"2026-07-06","cited_by_count":2,"area":"alignment"},{"id":"2509.23196","title":"From Harm to Help: Turning Reasoning In-Context Demos into Assets for Reasoning LMs","created":"2025-09-27","cited_by_count":1,"area":"lr"},{"id":"2511.03827","title":"STARS: Synchronous Token Alignment for Robust Supervision in Large Language Models","created":"2025-11-05","cited_by_count":1,"area":"alignment"},{"id":"2601.09259","title":"MAXS: Meta-Adaptive Exploration with LLM Agents","created":"2026-01-14","cited_by_count":1,"area":"lr"},{"id":"2604.20623","title":"RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-N Ranking","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2605.28224","title":"When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents?","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2605.30619","title":"Reward Learning from Best-of-$N$ Preference Data: Targets, Tradeoffs, and Design Principles","created":"2026-05-28","cited_by_count":1,"area":"alignment"},{"id":"2606.13732","title":"When Sample Selection Bias Precipitates Model Collapse","created":"2026-06-11","cited_by_count":1,"area":"synth"},{"id":"2609.35947","title":"FluxLite: Inference-Time Proposal Control for Discrete Diffusion Models","created":"2026-09-28","cited_by_count":1,"area":"diffusion"}],"next_cursor":"100"}